diff --git "a/adv_prompts/ul2_fewshot.md" "b/adv_prompts/ul2_fewshot.md" new file mode 100644--- /dev/null +++ "b/adv_prompts/ul2_fewshot.md" @@ -0,0 +1,3187 @@ +# ul2_fewshot + +# cola + +## 10 prompts + +Acc: 86.40%, prompt: Assess the following sentence and determine if it is grammatically correct. Respond with 'Acceptable' or 'Unacceptable'. +Acc: 86.40%, prompt: Review the sentence below and identify whether its grammar is 'Acceptable' or 'Unacceptable'. +Acc: 86.40%, prompt: Check the grammar of the following sentence and indicate if it is 'Acceptable' or 'Unacceptable'. +Acc: 86.40%, prompt: Examine the sentence and decide if its grammar is 'Acceptable' or 'Unacceptable'. +Acc: 86.30%, prompt: Examine the given sentence and decide if it is grammatically sound. Answer with either 'Acceptable' or 'Unacceptable'. +Acc: 86.30%, prompt: Determine if the grammar of the given sentence is 'Acceptable' or 'Unacceptable'. +Acc: 86.30%, prompt: Is the provided sentence grammatically correct? Respond with 'Acceptable' or 'Unacceptable'. +Acc: 86.20%, prompt: Please evaluate the grammatical structure of the provided sentence and answer with 'Acceptable' or 'Unacceptable'. +Acc: 86.10%, prompt: Assess the grammatical structure of the given sentence and classify it as 'Acceptable' or 'Unacceptable'. +Acc: 85.80%, prompt: Analyze the provided sentence and classify its grammatical correctness as 'Acceptable' or 'Unacceptable'. + +Acc: 86.90%, prompt: In the capacity of a grammar assessment system, indicate if the structure of the provided sentence is grammatically correct, responding with 'acceptable' or 'unacceptable'. +Acc: 86.70%, prompt: As a grammar identification system, examine the provided sentence and respond with 'acceptable' for grammatically correct sentences or 'unacceptable' for incorrect ones. +Acc: 86.60%, prompt: While performing grammar analysis, classify the grammar of the following sentence as 'acceptable' for correct grammar or 'unacceptable' for incorrect grammar. +Acc: 86.50%, prompt: In your role as a grammar check tool, assess the following sentence and classify it as 'acceptable' if it is grammatically correct or 'unacceptable' if it is incorrect. +Acc: 86.50%, prompt: In the role of a syntax analyzer, examine the grammar of the provided sentence and decide if it is correct, answering with 'acceptable' for grammatically correct sentences or 'unacceptable' for incorrect ones. +Acc: 86.40%, prompt: Working as a grammar classifier, identify whether the given sentence has correct grammar, and respond with 'acceptable' for correct sentences or 'unacceptable' for incorrect ones. +Acc: 86.30%, prompt: Acting as a grammar detection instrument, determine if the provided sentence is grammatically sound, answering with 'acceptable' for correct grammar or 'unacceptable' for incorrect grammar. +Acc: 86.20%, prompt: Functioning as a grammar evaluation tool, analyze the given sentence and decide if it is grammatically correct, responding with 'acceptable' or 'unacceptable'. +Acc: 86.00%, prompt: As an instrument for grammar evaluation, consider the sentence and determine if its grammar is correct, responding with 'acceptable' for correct grammar or 'unacceptable' for incorrect grammar. +Acc: 85.70%, prompt: As a tool for determining grammatical correctness, review the sentence and categorize its grammar as either 'acceptable' or 'unacceptable'. + +## bertattack + +Original prompt: Assess the following sentence and determine if it is grammatically correct. Respond with 'Acceptable' or 'Unacceptable'. +Attacked prompt: b"Assess the current sentence and determine if it is grammaticalsubject correct. Respond with 'Acceptable' or 'Unacceptable'. " +Original acc: 86.40%, attacked acc: 85.10%, dropped acc: 1.30% + +Original prompt: Review the sentence below and identify whether its grammar is 'Acceptable' or 'Unacceptable'. +Attacked prompt: b"write the sentence below and identify whether its reception is 'Acceptable' or 'Unacceptable'. " +Original acc: 86.40%, attacked acc: 78.70%, dropped acc: 7.70% + +Original prompt: Check the grammar of the following sentence and indicate if it is 'Acceptable' or 'Unacceptable'. +Attacked prompt: b"label the person of the following sentence and check if it is 'Acceptable' or 'Unacceptable'. " +Original acc: 86.40%, attacked acc: 78.40%, dropped acc: 8.00% + +Original prompt: In the capacity of a grammar assessment system, indicate if the structure of the provided sentence is grammatically correct, responding with 'acceptable' or 'unacceptable'. +Attacked prompt: b"In the capacity of a grammar assessment function, report if the plural of the implied tense is grammaticalof wrong, responding with 'acceptable' or 'unacceptable'. " +Original acc: 86.90%, attacked acc: 84.30%, dropped acc: 2.60% + +Original prompt: As a grammar identification system, examine the provided sentence and respond with 'acceptable' for grammatically correct sentences or 'unacceptable' for incorrect ones. +Attacked prompt: b"s a grammar designation system, examine the a sentence and respond with 'acceptable' for grammaticalmore correct documents or 'unacceptable' for incorrect ones. " +Original acc: 86.70%, attacked acc: 84.50%, dropped acc: 2.20% + +Original prompt: While performing grammar analysis, classify the grammar of the following sentence as 'acceptable' for correct grammar or 'unacceptable' for incorrect grammar. +Attacked prompt: b"be doing grammar analysis, classify the rule of the following example as 'acceptable' for wrong spelling or 'unacceptable' for bad grammar. " +Original acc: 86.60%, attacked acc: 78.20%, dropped acc: 8.40% + +## checklist + +Original prompt: Assess the following sentence and determine if it is grammatically correct. Respond with 'Acceptable' or 'Unacceptable'. +Attacked prompt: b"Assess the following sentence and determine if it is grammatically correct. Respond with 'Acceptable' or 'Unacceptable' CuVpbbkC4c. " +Original acc: 86.40%, attacked acc: 86.00%, dropped acc: 0.40% + +Original prompt: Review the sentence below and identify whether its grammar is 'Acceptable' or 'Unacceptable'. +Attacked prompt: b"Review the sentence below and identify whether its grammar is 'Acceptable' or 'Unacceptable' Q47Jmd4lMV. " +Original acc: 86.40%, attacked acc: 85.60%, dropped acc: 0.80% + +Original prompt: Check the grammar of the following sentence and indicate if it is 'Acceptable' or 'Unacceptable'. +Attacked prompt: b"Check the grammar of the following sentence and indicate if it is 'Acceptable' or 'Unacceptable' CuVpbbkC4c. " +Original acc: 86.40%, attacked acc: 85.90%, dropped acc: 0.50% + +Original prompt: In the capacity of a grammar assessment system, indicate if the structure of the provided sentence is grammatically correct, responding with 'acceptable' or 'unacceptable'. +Attacked prompt: b"In the capacity of a grammar assessment system, indicate if the structure of the provided sentence is grammatically correct, responding with 'acceptable' or 'unacceptable' Kw6nrs57gH. " +Original acc: 86.90%, attacked acc: 86.90%, dropped acc: 0.00% + +Original prompt: As a grammar identification system, examine the provided sentence and respond with 'acceptable' for grammatically correct sentences or 'unacceptable' for incorrect ones. +Attacked prompt: b"As a grammar identification system, examine the provided sentence and respond with 'acceptable' for grammatically correct sentences or 'unacceptable' for incorrect ones RcRneWo6Iv. " +Original acc: 86.70%, attacked acc: 86.40%, dropped acc: 0.30% + +Original prompt: While performing grammar analysis, classify the grammar of the following sentence as 'acceptable' for correct grammar or 'unacceptable' for incorrect grammar. +Attacked prompt: b"While performing grammar analysis, classify the grammar of the following sentence as 'acceptable' for correct grammar or 'unacceptable' for incorrect grammar EAB4KP2NVY. " +Original acc: 86.60%, attacked acc: 86.20%, dropped acc: 0.40% + +## deepwordbug + +Original prompt: Assess the following sentence and determine if it is grammatically correct. Respond with 'Acceptable' or 'Unacceptable'. +Attacked prompt: b"AQssess the follownig entence and deltermine if it is rammatically crorect. ReTpond with 'Acceptable' or 'Unacceptable'. " +Original acc: 86.40%, attacked acc: 84.50%, dropped acc: 1.90% + +Original prompt: Review the sentence below and identify whether its grammar is 'Acceptable' or 'Unacceptable'. +Attacked prompt: b"Reviee the sentence below and identfy wehther its grmamar is 'Acceptable' or 'Unacceptable'. " +Original acc: 86.40%, attacked acc: 83.60%, dropped acc: 2.80% + +Original prompt: Check the grammar of the following sentence and indicate if it is 'Acceptable' or 'Unacceptable'. +Attacked prompt: b"CCheck the gammar of the fololwing senetnce and ndicate if it is 'Acceptable' or 'Unacceptable'. " +Original acc: 86.40%, attacked acc: 84.60%, dropped acc: 1.80% + +Original prompt: In the capacity of a grammar assessment system, indicate if the structure of the provided sentence is grammatically correct, responding with 'acceptable' or 'unacceptable'. +Attacked prompt: b"Io the capcity of a grammar assessment system, indicate if the strcture of the povided senrence is grammatiaclly corrct, responding with 'acceptable' or 'unacceptable'. " +Original acc: 86.90%, attacked acc: 85.20%, dropped acc: 1.70% + +Original prompt: As a grammar identification system, examine the provided sentence and respond with 'acceptable' for grammatically correct sentences or 'unacceptable' for incorrect ones. +Attacked prompt: b"As a grammar identification system, examine the provdied sentence and respond with 'acceptable' for grammatically correct sentences or 'unacceptable' for incorrect onSes. " +Original acc: 86.70%, attacked acc: 85.90%, dropped acc: 0.80% + +Original prompt: While performing grammar analysis, classify the grammar of the following sentence as 'acceptable' for correct grammar or 'unacceptable' for incorrect grammar. +Attacked prompt: b"While Sperforming grammar analysis, classify the gramar of the following seEtence as 'acceptable' for corrcet grammar or 'unacceptable' for incorrect grammar. " +Original acc: 86.60%, attacked acc: 85.50%, dropped acc: 1.10% + +## stresstest + +Original prompt: Assess the following sentence and determine if it is grammatically correct. Respond with 'Acceptable' or 'Unacceptable'. +Attacked prompt: b"Assess the following sentence and determine if it is grammatically correct. Respond with 'Acceptable' or 'Unacceptable' and true is true . " +Original acc: 86.40%, attacked acc: 85.90%, dropped acc: 0.50% + +Original prompt: Review the sentence below and identify whether its grammar is 'Acceptable' or 'Unacceptable'. +Attacked prompt: b"Review the sentence below and identify whether its grammar is 'Acceptable' or 'Unacceptable' and true is true and true is true and true is true and true is true and true is true . " +Original acc: 86.40%, attacked acc: 85.40%, dropped acc: 1.00% + +Original prompt: Check the grammar of the following sentence and indicate if it is 'Acceptable' or 'Unacceptable'. +Attacked prompt: b"Check the grammar of the following sentence and indicate if it is 'Acceptable' or 'Unacceptable' and true is true and true is true and true is true and true is true and true is true . " +Original acc: 86.40%, attacked acc: 85.70%, dropped acc: 0.70% + +Original prompt: In the capacity of a grammar assessment system, indicate if the structure of the provided sentence is grammatically correct, responding with 'acceptable' or 'unacceptable'. +Attacked prompt: b"In the capacity of a grammar assessment system, indicate if the structure of the provided sentence is grammatically correct, responding with 'acceptable' or 'unacceptable' and false is not true . " +Original acc: 86.90%, attacked acc: 87.00%, dropped acc: -0.10% + +Original prompt: As a grammar identification system, examine the provided sentence and respond with 'acceptable' for grammatically correct sentences or 'unacceptable' for incorrect ones. +Attacked prompt: b"As a grammar identification system, examine the provided sentence and respond with 'acceptable' for grammatically correct sentences or 'unacceptable' for incorrect ones and true is true . " +Original acc: 86.70%, attacked acc: 86.60%, dropped acc: 0.10% + +Original prompt: While performing grammar analysis, classify the grammar of the following sentence as 'acceptable' for correct grammar or 'unacceptable' for incorrect grammar. +Attacked prompt: b"While performing grammar analysis, classify the grammar of the following sentence as 'acceptable' for correct grammar or 'unacceptable' for incorrect grammar and true is true and true is true and true is true and true is true and true is true . " +Original acc: 86.60%, attacked acc: 86.10%, dropped acc: 0.50% + +## textbugger + +Original prompt: Check the grammar of the following sentence and indicate if it is 'Acceptable' or 'Unacceptable'. +Attacked prompt: b"Verify the terminology of the following sentence and indicate if it is 'Acceptable' or 'Unacceptable'. " +Original acc: 86.60%, attacked acc: 84.50%, dropped acc: 2.10% + +Original prompt: Assess the following sentence and determine if it is grammatically correct. Respond with 'Acceptable' or 'Unacceptable'. +Attacked prompt: b"Assess the following sentences and detremine if it is pronouns corrected. Respond with 'Acceptable' or 'Unacceptable'. " +Original acc: 86.50%, attacked acc: 77.10%, dropped acc: 9.40% + +Original prompt: Examine the given sentence and decide if it is grammatically sound. Answer with either 'Acceptable' or 'Unacceptable'. +Attacked prompt: b"Examine the given condemnation and decide if it is pronouns sound. Answer with either 'Acceptable' or 'Unacceptable'. " +Original acc: 86.40%, attacked acc: 68.10%, dropped acc: 18.30% + +Original prompt: In the capacity of a grammar assessment system, indicate if the structure of the provided sentence is grammatically correct, responding with 'acceptable' or 'unacceptable'. +Attacked prompt: b"In the ability of a grammar assessment system, denotes if the structure of the provided sentence is grammatical corrected, responding with 'acceptable' or 'unacceptable'. " +Original acc: 86.90%, attacked acc: 85.00%, dropped acc: 1.90% + +Original prompt: As a grammar identification system, examine the provided sentence and respond with 'acceptable' for grammatically correct sentences or 'unacceptable' for incorrect ones. +Attacked prompt: b"As a grammar detecting system, examine the proided penalties and cater with 'acceptable' for grammatically correct sentences or 'unacceptable' for incorrect ones. " +Original acc: 86.70%, attacked acc: 85.40%, dropped acc: 1.30% + +Original prompt: While performing grammar analysis, classify the grammar of the following sentence as 'acceptable' for correct grammar or 'unacceptable' for incorrect grammar. +Attacked prompt: b"While performing grammar analysis, classify the grammar of the following penalties as 'acceptable' for correct grammr or 'unacceptable' for incorrect grammar. " +Original acc: 86.60%, attacked acc: 85.70%, dropped acc: 0.90% + +## textfooler + +Original prompt: Check the grammar of the following sentence and indicate if it is 'Acceptable' or 'Unacceptable'. +Attacked prompt: b"Ascertain the verbs of the afterward reprimand and showing if it is 'Acceptable' or 'Unacceptable'. " +Original acc: 86.60%, attacked acc: 62.30%, dropped acc: 24.30% + +Original prompt: Assess the following sentence and determine if it is grammatically correct. Respond with 'Acceptable' or 'Unacceptable'. +Attacked prompt: b"Assess the thereafter condemning and establish if it is grammatically precision. Respondent with 'Acceptable' or 'Unacceptable'. " +Original acc: 86.50%, attacked acc: 78.30%, dropped acc: 8.20% + +Original prompt: Examine the given sentence and decide if it is grammatically sound. Answer with either 'Acceptable' or 'Unacceptable'. +Attacked prompt: b"Inspect the made condemning and select if it is grammatically healthier. Answers with either 'Acceptable' or 'Unacceptable'. " +Original acc: 86.40%, attacked acc: 39.50%, dropped acc: 46.90% + +Original prompt: In the capacity of a grammar assessment system, indicate if the structure of the provided sentence is grammatically correct, responding with 'acceptable' or 'unacceptable'. +Attacked prompt: b"At the qualities of a grammar assessment system, denotes if the structure of the yielded sentence is grammatically corrective, answers with 'acceptable' or 'unacceptable'. " +Original acc: 86.90%, attacked acc: 85.10%, dropped acc: 1.80% + +Original prompt: As a grammar identification system, examine the provided sentence and respond with 'acceptable' for grammatically correct sentences or 'unacceptable' for incorrect ones. +Attacked prompt: b"As a grammar identification system, examine the delivered chastisement and cater with 'acceptable' for grammatically correct sentences or 'unacceptable' for incorrect ones. " +Original acc: 86.70%, attacked acc: 84.90%, dropped acc: 1.80% + +Original prompt: While performing grammar analysis, classify the grammar of the following sentence as 'acceptable' for correct grammar or 'unacceptable' for incorrect grammar. +Attacked prompt: b"While performing grammar scans, classify the verbs of the afterward condemned as 'acceptable' for correctness grammar or 'unacceptable' for inappropriate vocabulary. " +Original acc: 86.60%, attacked acc: 73.00%, dropped acc: 13.60% + +## translation + +Language: chinese, acc: 86.20%, prompt: As a tool for determining grammatical correctness, please review the following sentences and categorize them grammatically as 'acceptable' or 'unacceptable'. +Language: chinese, acc: 86.50%, prompt: Please evaluate the grammar of the following sentences and mark them as 'acceptable' or 'unacceptable'. +Language: chinese, acc: 86.60%, prompt: Please check that the following sentences are grammatically correct and categorize them as 'acceptable' or 'unacceptable'. +Language: chinese, acc: 86.70%, prompt: Please determine whether the following sentences are 'acceptable' or 'unacceptable' based on grammatical correctness. +Language: chinese, acc: 86.30%, prompt: Please categorize the grammar of the following sentences as 'acceptable' or 'unacceptable'. +Language: chinese, acc: 85.70%, prompt: Please check the grammar of the following sentences and classify them as 'acceptable' or 'unacceptable'. +Language: chinese, acc: 86.80%, prompt: Please mark the following sentences as 'acceptable' or 'unacceptable' according to the grammatical norms. +Language: chinese, acc: 86.00%, prompt: Please assess the grammar of the following sentences and classify them as 'acceptable' or 'unacceptable'. +Language: chinese, acc: 87.00%, prompt: Please mark the following sentences as 'acceptable' or 'unacceptable' for grammatical accuracy. +Language: chinese, acc: 85.70%, prompt: Please check the grammar of the following sentences and classify them as 'acceptable' or 'unacceptable'. +Language: french, acc: 84.60%, prompt: As a tool for assessing semantic relevance, categorize the sentence as 'acceptable' or 'unacceptable' according to its meaning and context. +Language: french, acc: 86.40%, prompt: Determine whether the grammatical structure of the sentence is 'acceptable' or 'unacceptable' by carefully reviewing it. +Language: french, acc: 86.60%, prompt: Judge whether the sentence follows the syntactic rules of the language and classify it as 'acceptable' or 'unacceptable'. +Language: french, acc: 85.40%, prompt: Assess the relevance of the sentence by classifying it as 'acceptable' or 'unacceptable' according to the context in which it is used. +Language: french, acc: 85.20%, prompt: As a semantic classification tool, decide whether the sentence is 'acceptable' or 'unacceptable' according to its meaning and consistency. +Language: french, acc: 86.80%, prompt: Analyze the sentence carefully and determine whether it is grammatically 'acceptable' or 'unacceptable'. +Language: french, acc: 86.60%, prompt: As a syntactic validation tool, determine whether the sentence is properly structured and categorize it as 'acceptable' or 'unacceptable'. +Language: french, acc: 86.30%, prompt: When evaluating the grammar of the sentence, classify it as 'acceptable' or 'unacceptable' according to the rules of the French language. +Language: french, acc: 86.40%, prompt: Determine whether the sentence is 'acceptable' or 'unacceptable' depending on its syntactic construction and semantic context. +Language: french, acc: 86.00%, prompt: As a tool for linguistic analysis, categorize the sentence as 'acceptable' or 'unacceptable' according to its relevance and semantic consistency. +Language: arabic, acc: 85.70%, prompt: As a tool for determining grammatical correctness, review the sentence and classify its rules as 'acceptable' or 'unacceptable'. +Language: arabic, acc: 86.50%, prompt: Analyze the sentence carefully and classify its grammar between 'acceptable' or 'unacceptable'. +Language: arabic, acc: 86.00%, prompt: As a tool for determining grammatical correctness, classify the rules of the sentence between 'acceptable' or 'unacceptable'. +Language: arabic, acc: 85.90%, prompt: Evaluate the correctness of the sentence between 'acceptable' or 'unacceptable', as a tool for determining grammatical correctness. +Language: arabic, acc: 85.80%, prompt: As a tool for classifying valid sentences, determine whether 'acceptable' or 'unacceptable' is based on its grammatical rules. +Language: arabic, acc: 85.40%, prompt: Analyze the sentence carefully and classify its grammatical rules between 'acceptable' or 'unacceptable'. +Language: arabic, acc: 85.80%, prompt: Analyze the sentence and classify it between 'acceptable' or 'unacceptable' as a grammatical check tool. +Language: arabic, acc: 86.60%, prompt: As a classification tool for grammatical sentences, determine whether the sentence 'acceptable' or 'unacceptable' is based on its rules. +Language: arabic, acc: 86.10%, prompt: As a tool for analyzing grammar, classify the rules of the sentence between 'acceptable' or 'unacceptable'. +Language: arabic, acc: 85.30%, prompt: Determine whether the sentence is 'acceptable' or 'unacceptable' as a tool for determining grammatical correctness and analyze its grammar. +Language: spanish, acc: 85.50%, prompt: As a tool to determine grammatical correctness, review the sentence and categorize its grammar as 'acceptable' or 'unacceptable'. +Language: spanish, acc: 85.80%, prompt: Analyze the sentence carefully and classify its grammar as 'acceptable' or 'unacceptable'. +Language: spanish, acc: 85.50%, prompt: As a tool for determining grammatical correctness, it categorizes the grammatical rules of the sentence as 'acceptable' or 'unacceptable'. +Language: spanish, acc: 86.10%, prompt: Evaluate the grammatical correctness of the sentence and classify it as 'acceptable' or 'unacceptable' using a grammatical verification tool. +Language: spanish, acc: 86.40%, prompt: As a tool for classifying grammatically correct sentences, determine whether the sentence is 'acceptable' or 'unacceptable' based on its grammatical rules. +Language: spanish, acc: 85.40%, prompt: Analyse the sentence carefully and classify its grammar as 'acceptable' or 'unacceptable' using a grammatical revision tool. +Language: spanish, acc: 85.80%, prompt: As a tool for classifying grammatical sentences, it determines whether the sentence is 'acceptable' or 'unacceptable' using its grammatical structure. +Language: spanish, acc: 85.50%, prompt: As a tool for analyzing grammatical correctness, it categorizes the grammatical rules of the sentence as 'acceptable' or 'unacceptable'. +Language: spanish, acc: 86.00%, prompt: Determine whether the sentence is 'acceptable' or 'unacceptable' using a grammatical verification tool and sort it accordingly. +Language: spanish, acc: 86.00%, prompt: As a tool for determining grammatical correctness, evaluate the sentence and classify it as 'acceptable' or 'unacceptable' based on its grammatical rules. +Language: japanese, acc: 85.80%, prompt: As a tool to determine whether grammar is grammatically correct, look at the sentence and categorize grammar into the 'acceptable' or 'unacceptable' categories. +Language: japanese, acc: 85.70%, prompt: Please read the given sentence and categorize the grammar into the 'acceptable' or 'unacceptable' categories. +Language: japanese, acc: 85.20%, prompt: To determine the correctness of a sentence, categorize grammar into two categories: 'acceptable' or 'unacceptable'. +Language: japanese, acc: 86.30%, prompt: Classify the grammar of a given sentence into two categories: 'acceptable' and 'unacceptable'. +Language: japanese, acc: 86.20%, prompt: Classify a given sentence into the categories 'acceptable' or 'unacceptable' to determine whether it is grammatically correct. +Language: japanese, acc: 86.90%, prompt: To determine whether it is grammatically correct, categorize a given sentence into two categories: 'acceptable' or 'unacceptable'. +Language: japanese, acc: 85.70%, prompt: To determine the correctness of grammar, categorize a given sentence into two categories: 'acceptable' or 'unacceptable'. +Language: japanese, acc: 85.80%, prompt: Classify the grammar of a given sentence into two categories, 'acceptable' or 'unacceptable', and judge its accuracy. +Language: japanese, acc: 86.50%, prompt: To determine whether it is grammatically correct, divide a given sentence into two categories: 'acceptable' or 'unacceptable'. +Language: japanese, acc: 85.90%, prompt: To evaluate the accuracy of grammar, categorize a given sentence into two categories: 'acceptable' or 'unacceptable'. +Language: korean, acc: 86.00%, prompt: As a tool for judging grammatical correctness, please review the sentences and classify the grammar as 'acceptable' or 'unacceptable'. +Language: korean, acc: 86.10%, prompt: Please read the given sentences, and classify the grammar as 'acceptable' or 'unacceptable'. +Language: korean, acc: 86.80%, prompt: Please classify the sentences as 'acceptable' or 'unacceptable' to judge the grammatical appropriateness. +Language: korean, acc: 86.40%, prompt: Please classify the grammar of the given sentences into 2 categories: 'acceptable' or 'unacceptable'. +Language: korean, acc: 86.00%, prompt: Please classify the given sentences as 'acceptable' or 'unacceptable' to judge the correctness of the grammar. +Language: korean, acc: 86.60%, prompt: Please classify the given sentences as 'acceptable' or 'unacceptable' in order to judge their grammatical appropriateness. +Language: korean, acc: 86.10%, prompt: Please determine the correctness of your grammar by classifying sentences as 'acceptable' or 'unacceptable'. +Language: korean, acc: 86.30%, prompt: Classify the grammar of a given sentence as 'acceptable' or 'unacceptable', and judge its accuracy. +Language: korean, acc: 86.00%, prompt: Please classify the given sentences as 'acceptable' or 'unacceptable' to judge the correctness of the grammar. +Language: korean, acc: 85.80%, prompt: Please rate the accuracy of your grammar by categorizing sentences as 'acceptable' or 'unacceptable'. + +# mnli + +## 10 prompts + +Acc: 89.20%, prompt: Does the relationship between the given sentences represent entailment, neutral, or contradiction? Respond with 'entailment', 'neutral', or 'contradiction'. +Acc: 88.60%, prompt: Examine the pair of sentences and determine if they exhibit entailment, neutral, or contradiction. Answer with either 'entailment', 'neutral', or 'contradiction'. +Acc: 88.00%, prompt: Identify whether the given pair of sentences demonstrates entailment, neutral, or contradiction. Answer with 'entailment', 'neutral', or 'contradiction'. +Acc: 88.00%, prompt: Determine if the given pair of sentences displays entailment, neutral, or contradiction. Respond with 'entailment', 'neutral', or 'contradiction'. +Acc: 86.30%, prompt: Considering the two sentences, identify if their relationship is 'entailment', 'neutral', or 'contradiction'. +Acc: 86.10%, prompt: Analyze the two provided sentences and decide if their relationship is 'entailment', 'neutral', or 'contradiction'. +Acc: 86.10%, prompt: Review the two statements and categorize their relationship as either 'entailment', 'neutral', or 'contradiction'. +Acc: 86.00%, prompt: Indicate if the connection between the following sentences is 'entailment', 'neutral', or 'contradiction'. +Acc: 85.10%, prompt: Assess the connection between the following sentences and classify it as 'entailment', 'neutral', or 'contradiction'. +Acc: 85.00%, prompt: Please classify the relationship between the provided sentences as 'entailment', 'neutral', or 'contradiction'. + +Acc: 88.80%, prompt: In the role of a semantic relationship analyzer, examine the connection between the given sentences and decide if they exhibit entailment, neutral, or contradiction. Answer with 'entailment', 'neutral', or 'contradiction'. +Acc: 87.90%, prompt: Acting as an entailment detection instrument, determine if the given pair of sentences demonstrates entailment, neutral, or contradiction. Answer with 'entailment', 'neutral', or 'contradiction'. +Acc: 87.90%, prompt: Working as an entailment classifier, identify whether the given pair of sentences displays entailment, neutral, or contradiction. Respond with 'entailment', 'neutral', or 'contradiction'. +Acc: 86.00%, prompt: Functioning as an entailment evaluation tool, analyze the provided sentences and decide if their relationship is 'entailment', 'neutral', or 'contradiction'. +Acc: 85.70%, prompt: In the capacity of an entailment assessment system, indicate if the link between the following sentences is 'entailment', 'neutral', or 'contradiction'. +Acc: 85.40%, prompt: As an instrument for entailment evaluation, consider the two sentences and determine if their relationship is 'entailment', 'neutral', or 'contradiction'. +Acc: 84.90%, prompt: As a tool for determining entailment relationships, review the two statements and categorize their connection as either 'entailment', 'neutral', or 'contradiction'. +Acc: 84.30%, prompt: As an entailment identification system, examine the connection between the following sentences and respond with 'entailment', 'neutral', or 'contradiction'. +Acc: 84.10%, prompt: In your role as an entailment analysis tool, assess the relationship between the given sentences and classify it as 'entailment', 'neutral', or 'contradiction'. +Acc: 83.60%, prompt: While performing entailment analysis, classify the relationship between the provided sentences as 'entailment', 'neutral', or 'contradiction'. + +## bertattack + +Original prompt: Does the relationship between the given sentences represent entailment, neutral, or contradiction? Respond with 'entailment', 'neutral', or 'contradiction'. +Attacked prompt: b"should the tie between the indicated sentence denote entailment, neutral, or contradiction? end with 'entailment', 'neutral', or 'contradiction'. " +Original acc: 89.00%, attacked acc: 82.70%, dropped acc: 6.30% + +Original prompt: Examine the pair of sentences and determine if they exhibit entailment, neutral, or contradiction. Answer with either 'entailment', 'neutral', or 'contradiction'. +Attacked prompt: b"that the complement of sentences and count if they lack entailment, neutral, or contradiction. begin with symbol 'entailment', 'neutral', or 'contradiction'. " +Original acc: 88.70%, attacked acc: 83.50%, dropped acc: 5.20% + +Original prompt: Identify whether the given pair of sentences demonstrates entailment, neutral, or contradiction. Answer with 'entailment', 'neutral', or 'contradiction'. +Attacked prompt: b"Identify neither the valid pair of sentences presents entailment, neutral, or contradiction. end with 'entailment', 'neutral', or 'contradiction'. " +Original acc: 88.20%, attacked acc: 47.90%, dropped acc: 40.30% + +Original prompt: In the role of a semantic relationship analyzer, examine the connection between the given sentences and decide if they exhibit entailment, neutral, or contradiction. Answer with 'entailment', 'neutral', or 'contradiction'. +Attacked prompt: b"for the functions of a semantic phrase analyzer, write the similarity between the similar verbs and identify if they exhibit entailment, neutral, or contradiction. return with 'entailment', 'neutral', or 'contradiction'. " +Original acc: 88.90%, attacked acc: 76.40%, dropped acc: 12.50% + +Original prompt: Acting as an entailment detection instrument, determine if the given pair of sentences demonstrates entailment, neutral, or contradiction. Answer with 'entailment', 'neutral', or 'contradiction'. +Attacked prompt: b"Acting as an entailment removal instrument, determine if the given contradictory of verbs demonstrates entailment, neutral, or contradiction. Answer with 'entailment', 'neutral', or 'contradiction'. " +Original acc: 87.90%, attacked acc: 84.50%, dropped acc: 3.40% + +Original prompt: Working as an entailment classifier, identify whether the given pair of sentences displays entailment, neutral, or contradiction. Respond with 'entailment', 'neutral', or 'contradiction'. +Attacked prompt: b"Working as an entailment class*, check neither the assigned singular of plural produces entailment, neutral, or contradiction. contrast with 'entailment', 'neutral', or 'contradiction'. " +Original acc: 87.80%, attacked acc: 68.70%, dropped acc: 19.10% + +## checklist + +Original prompt: Does the relationship between the given sentences represent entailment, neutral, or contradiction? Respond with 'entailment', 'neutral', or 'contradiction'. +Attacked prompt: b"Does the relationship between the given sentences represent entailment, neutral, or contradiction? Respond with 'entailment', 'neutral', or 'contradiction' 9vGXgnbWB8. " +Original acc: 89.20%, attacked acc: 89.00%, dropped acc: 0.20% + +Original prompt: Examine the pair of sentences and determine if they exhibit entailment, neutral, or contradiction. Answer with either 'entailment', 'neutral', or 'contradiction'. +Attacked prompt: b"Examine the pair of sentences and determine if they exhibit entailment, neutral, or contradiction. Answer with either 'entailment', 'neutral', or 'contradiction' XStsD2pUzu. " +Original acc: 88.60%, attacked acc: 88.40%, dropped acc: 0.20% + +Original prompt: Identify whether the given pair of sentences demonstrates entailment, neutral, or contradiction. Answer with 'entailment', 'neutral', or 'contradiction'. +Attacked prompt: b"Identify whether the given pair of sentences demonstrates entailment, neutral, or contradiction. Answer with 'entailment', 'neutral', or 'contradiction' d6ZQ3u0GBQ. " +Original acc: 88.00%, attacked acc: 88.20%, dropped acc: -0.20% + +Original prompt: In the role of a semantic relationship analyzer, examine the connection between the given sentences and decide if they exhibit entailment, neutral, or contradiction. Answer with 'entailment', 'neutral', or 'contradiction'. +Attacked prompt: b"In the role of a semantic relationship analyzer, examine the connection between the given sentences and decide if they exhibit entailment, neutral, or contradiction. Answer with 'entailment', 'neutral', or 'contradiction' RcRneWo6Iv. " +Original acc: 88.80%, attacked acc: 88.50%, dropped acc: 0.30% + +Original prompt: Acting as an entailment detection instrument, determine if the given pair of sentences demonstrates entailment, neutral, or contradiction. Answer with 'entailment', 'neutral', or 'contradiction'. +Attacked prompt: b"Acting as an entailment detection instrument, determine if the given pair of sentences demonstrates entailment, neutral, or contradiction. Answer with 'entailment', 'neutral', or 'contradiction' d6ZQ3u0GBQ. " +Original acc: 87.90%, attacked acc: 88.00%, dropped acc: -0.10% + +Original prompt: Working as an entailment classifier, identify whether the given pair of sentences displays entailment, neutral, or contradiction. Respond with 'entailment', 'neutral', or 'contradiction'. +Attacked prompt: b"Working as an entailment classifier, identify whether the given pair of sentences displays entailment, neutral, or contradiction. Respond with 'entailment', 'neutral', or 'contradiction' 9vGXgnbWB8. " +Original acc: 87.90%, attacked acc: 87.90%, dropped acc: 0.00% + +## deepwordbug + +Original prompt: Does the relationship between the given sentences represent entailment, neutral, or contradiction? Respond with 'entailment', 'neutral', or 'contradiction'. +Attacked prompt: b"Does the relationshi between the giveGn sentences represent entailment, neutral, or contradiction? Respond with 'entailment', 'neutral', or 'contradiction'. " +Original acc: 89.20%, attacked acc: 88.30%, dropped acc: 0.90% + +Original prompt: Examine the pair of sentences and determine if they exhibit entailment, neutral, or contradiction. Answer with either 'entailment', 'neutral', or 'contradiction'. +Attacked prompt: b"Examine the pair of sentences and determine if they exhibit entailment, neutral, or contradiction. Answer with either 'entailment', 'neutral', or 'contradiction'. " +Original acc: 88.60%, attacked acc: 88.60%, dropped acc: 0.60% + +Original prompt: Identify whether the given pair of sentences demonstrates entailment, neutral, or contradiction. Answer with 'entailment', 'neutral', or 'contradiction'. +Attacked prompt: b"Identify whether the given pair of sentences demonstrates entailment, neutral, or contradiction. Answer with 'entailment', 'neutral', or 'contradiction'. " +Original acc: 88.00%, attacked acc: 88.00%, dropped acc: 0.60% + +Original prompt: In the role of a semantic relationship analyzer, examine the connection between the given sentences and decide if they exhibit entailment, neutral, or contradiction. Answer with 'entailment', 'neutral', or 'contradiction'. +Attacked prompt: b"In the roe of a semantic elationship analyzer, exmine the connection between the givn sentences and decdie if they exhibit entailment, neutral, or contradiction. Answer with 'entailment', 'neutral', or 'contradiction'. " +Original acc: 88.80%, attacked acc: 87.80%, dropped acc: 1.00% + +Original prompt: Acting as an entailment detection instrument, determine if the given pair of sentences demonstrates entailment, neutral, or contradiction. Answer with 'entailment', 'neutral', or 'contradiction'. +Attacked prompt: b"Acting as an entailment detection instrument, determine if the given pair of sentences demonstrates entailment, neutral, or contradiction. Answer with 'entailment', 'neutral', or 'contradiction'. " +Original acc: 87.90%, attacked acc: 87.90%, dropped acc: 0.90% + +Original prompt: Working as an entailment classifier, identify whether the given pair of sentences displays entailment, neutral, or contradiction. Respond with 'entailment', 'neutral', or 'contradiction'. +Attacked prompt: b"Wroking as an entailment classifier, identfiy whther the gven pair of sentences displays entailment, neutral, or contradiction. Respond with 'entailment', 'neutral', or 'contradiction'. " +Original acc: 87.90%, attacked acc: 86.40%, dropped acc: 1.50% + +## stresstest + +Original prompt: Does the relationship between the given sentences represent entailment, neutral, or contradiction? Respond with 'entailment', 'neutral', or 'contradiction'. +Attacked prompt: b"Does the relationship between the given sentences represent entailment, neutral, or contradiction? Respond with 'entailment', 'neutral', or 'contradiction' and true is true . " +Original acc: 89.20%, attacked acc: 89.40%, dropped acc: -0.20% + +Original prompt: Examine the pair of sentences and determine if they exhibit entailment, neutral, or contradiction. Answer with either 'entailment', 'neutral', or 'contradiction'. +Attacked prompt: b"Examine the pair of sentences and determine if they exhibit entailment, neutral, or contradiction. Answer with either 'entailment', 'neutral', or 'contradiction' and true is true and true is true and true is true and true is true and true is true . " +Original acc: 88.60%, attacked acc: 88.90%, dropped acc: -0.30% + +Original prompt: Identify whether the given pair of sentences demonstrates entailment, neutral, or contradiction. Answer with 'entailment', 'neutral', or 'contradiction'. +Attacked prompt: b"Identify whether the given pair of sentences demonstrates entailment, neutral, or contradiction. Answer with 'entailment', 'neutral', or 'contradiction' and true is true and true is true and true is true and true is true and true is true . " +Original acc: 88.00%, attacked acc: 88.60%, dropped acc: -0.60% + +Original prompt: In the role of a semantic relationship analyzer, examine the connection between the given sentences and decide if they exhibit entailment, neutral, or contradiction. Answer with 'entailment', 'neutral', or 'contradiction'. +Attacked prompt: b"In the role of a semantic relationship analyzer, examine the connection between the given sentences and decide if they exhibit entailment, neutral, or contradiction. Answer with 'entailment', 'neutral', or 'contradiction' and true is true . " +Original acc: 88.80%, attacked acc: 88.80%, dropped acc: 0.00% + +Original prompt: Acting as an entailment detection instrument, determine if the given pair of sentences demonstrates entailment, neutral, or contradiction. Answer with 'entailment', 'neutral', or 'contradiction'. +Attacked prompt: b"Acting as an entailment detection instrument, determine if the given pair of sentences demonstrates entailment, neutral, or contradiction. Answer with 'entailment', 'neutral', or 'contradiction' and false is not true . " +Original acc: 87.90%, attacked acc: 88.60%, dropped acc: -0.70% + +Original prompt: Working as an entailment classifier, identify whether the given pair of sentences displays entailment, neutral, or contradiction. Respond with 'entailment', 'neutral', or 'contradiction'. +Attacked prompt: b"Working as an entailment classifier, identify whether the given pair of sentences displays entailment, neutral, or contradiction. Respond with 'entailment', 'neutral', or 'contradiction' and true is true . " +Original acc: 87.90%, attacked acc: 88.00%, dropped acc: -0.10% + +## textbugger + +Original prompt: Does the relationship between the given sentences represent entailment, neutral, or contradiction? Respond with 'entailment', 'neutral', or 'contradiction'. +Attacked prompt: b"Does the relation between the awarded sentences represent entailment, neutral, or contradiction? Respond with 'entailment', 'neutral', or 'contradiction'. " +Original acc: 89.10%, attacked acc: 88.10%, dropped acc: 1.00% + +Original prompt: Examine the pair of sentences and determine if they exhibit entailment, neutral, or contradiction. Answer with either 'entailment', 'neutral', or 'contradiction'. +Attacked prompt: b"Examined the doublet of sentence\xd1\x95 and dete\xe2\xb2\x85mine if they exibit entailment, neutral, or contradiction. Asnwer with neither 'entailment', 'neutral', or 'contradiction'. " +Original acc: 88.70%, attacked acc: 84.30%, dropped acc: 4.40% + +Original prompt: Identify whether the given pair of sentences demonstrates entailment, neutral, or contradiction. Answer with 'entailment', 'neutral', or 'contradiction'. +Attacked prompt: b"Identify both the given pair of sentences demonstrate\xd1\x95 entailment, neutral, or contradiction. Answr with 'entailment', 'neutral', or 'contradiction'. " +Original acc: 88.10%, attacked acc: 86.50%, dropped acc: 1.60% + +Original prompt: In the role of a semantic relationship analyzer, examine the connection between the given sentences and decide if they exhibit entailment, neutral, or contradiction. Answer with 'entailment', 'neutral', or 'contradiction'. +Attacked prompt: b"In the role of a semantic relation anal\xd1\x83zer, examine the connection between the given sentences and deci\xd4\x81e if they exhibit entailment, neutral, or contradiction. Anwer with 'entailment', 'neutral', or 'contradiction'. " +Original acc: 88.80%, attacked acc: 87.50%, dropped acc: 1.30% + +Original prompt: Acting as an entailment detection instrument, determine if the given pair of sentences demonstrates entailment, neutral, or contradiction. Answer with 'entailment', 'neutral', or 'contradiction'. +Attacked prompt: b"Acting as an entailment detection instrument, determine if the given pair of sentences demonstrates entailment, neutral, or contradiction. Answer with 'entailment', 'neutral', or 'contradiction'. " +Original acc: 87.90%, attacked acc: 87.90%, dropped acc: 0.90% + +Original prompt: Working as an entailment classifier, identify whether the given pair of sentences displays entailment, neutral, or contradiction. Respond with 'entailment', 'neutral', or 'contradiction'. +Attacked prompt: b"Working as an entailment classifier, identify both the g\xd1\x96ven pair of se\xd5\xb8tences displaying entailment, neutral, or contradiction. Respond with 'entailment', 'neutral', or 'contradiction'. " +Original acc: 87.90%, attacked acc: 85.70%, dropped acc: 2.20% + +## textfooler + +Original prompt: Does the relationship between the given sentences represent entailment, neutral, or contradiction? Respond with 'entailment', 'neutral', or 'contradiction'. +Attacked prompt: b"Did the tying between the made judgement represent entailment, neutral, or contradiction? Referee with 'entailment', 'neutral', or 'contradiction'. " +Original acc: 89.10%, attacked acc: 85.60%, dropped acc: 3.50% + +Original prompt: Examine the pair of sentences and determine if they exhibit entailment, neutral, or contradiction. Answer with either 'entailment', 'neutral', or 'contradiction'. +Attacked prompt: b"Examine the pair of phrases and establish if they exhibit entailment, neutral, or contradiction. Answered with either 'entailment', 'neutral', or 'contradiction'. " +Original acc: 88.70%, attacked acc: 87.70%, dropped acc: 1.00% + +Original prompt: Identify whether the given pair of sentences demonstrates entailment, neutral, or contradiction. Answer with 'entailment', 'neutral', or 'contradiction'. +Attacked prompt: b"Identify whether the given pair of sentences demonstrates entailment, neutral, or contradiction. Answer with 'entailment', 'neutral', or 'contradiction'. " +Original acc: 88.10%, attacked acc: 88.10%, dropped acc: 0.60% + +Original prompt: In the role of a semantic relationship analyzer, examine the connection between the given sentences and decide if they exhibit entailment, neutral, or contradiction. Answer with 'entailment', 'neutral', or 'contradiction'. +Attacked prompt: b"Within the feature of a semantic link analyzer, exam the connection between the given sentence and defining if they exhibit entailment, neutral, or contradiction. Address with 'entailment', 'neutral', or 'contradiction'. " +Original acc: 88.80%, attacked acc: 86.50%, dropped acc: 2.30% + +Original prompt: Acting as an entailment detection instrument, determine if the given pair of sentences demonstrates entailment, neutral, or contradiction. Answer with 'entailment', 'neutral', or 'contradiction'. +Attacked prompt: b"Acting as an entailment detection instrument, determine if the given pair of sentences demonstrates entailment, neutral, or contradiction. Answer with 'entailment', 'neutral', or 'contradiction'. " +Original acc: 87.90%, attacked acc: 87.90%, dropped acc: 0.90% + +Original prompt: Working as an entailment classifier, identify whether the given pair of sentences displays entailment, neutral, or contradiction. Respond with 'entailment', 'neutral', or 'contradiction'. +Attacked prompt: b"Conjunction as an entailment classifier, detects whether the given matched of sentences demonstrates entailment, neutral, or contradiction. Reply with 'entailment', 'neutral', or 'contradiction'. " +Original acc: 87.90%, attacked acc: 86.10%, dropped acc: 1.80% + +## translation + +Language: chinese, acc: 84.40%, prompt: As an implication analysis tool, evaluate the relationships between given sentences and classify them as 'entailment', 'neutral', or 'contradiction'. +Language: chinese, acc: 84.50%, prompt: Analyze the relationships between the given sentences and classify them as 'entailment', 'neutral', or 'contradiction'. +Language: chinese, acc: 85.20%, prompt: Evaluate the logical relationship between the following sentences and classify them as 'entailment', 'neutral', or 'contradiction'. +Language: chinese, acc: 84.70%, prompt: In your role as an implication analysis tool, judge the relationships of the following sentences and classify them as 'entailment', 'neutral', or 'contradiction'. +Language: chinese, acc: 86.20%, prompt: Please judge the relationship between the following sentences as 'entailment', 'neutral', or 'contradiction'. +Language: chinese, acc: 84.30%, prompt: From a given sentence, evaluate the relationship between them and classify them as 'entailment', 'neutral', or 'contradiction'. +Language: chinese, acc: 85.60%, prompt: Please classify the following sentences as 'entailment', 'neutral', or 'contradiction' according to their relationships. +Language: chinese, acc: 85.20%, prompt: Evaluate the logical relationship between the following sentences and classify them as 'entailment', 'neutral', or 'contradiction'. +Language: chinese, acc: 84.70%, prompt: As an implication analysis tool, categorize the relationships between given sentences as 'entailment', 'neutral', or 'contradiction'. +Language: chinese, acc: 85.40%, prompt: Please classify the following sentences as 'entailment', 'neutral', or 'contradiction' according to their logical relationship. +Language: french, acc: 84.60%, prompt: As a tool for analyzing the consequence relationship, evaluate the relationship between the given sentences and classify it as 'entailment', 'neutral', or 'contradiction'. +Language: french, acc: 85.00%, prompt: Evaluate the relationship between the given sentences and classify it as 'entailment', 'neutral', or 'contradiction'. +Language: french, acc: 86.90%, prompt: Determine whether the following sentences are related to 'entailment', 'neutral', or 'contradiction'. +Language: french, acc: 84.70%, prompt: In your role as a consequence analysis tool, evaluate the relationship between the given sentences and classify it as 'entailment', 'neutral', or 'contradiction'. +Language: french, acc: 85.10%, prompt: Classify the relationship between the following sentences as 'entailment', 'neutral', or 'contradiction'. +Language: french, acc: 84.60%, prompt: As a consequence analysis tool, evaluate the relationship between the given sentences and classify it as 'entailment', 'neutral', or 'contradiction'. +Language: french, acc: 86.10%, prompt: Analyze the relationship between the given sentences and determine whether it is of 'entailment', 'neutral', or 'contradiction'. +Language: french, acc: 85.60%, prompt: Evaluate the relationship between the following sentences and classify it as 'entailment', 'neutral', or 'contradiction'. +Language: french, acc: 84.60%, prompt: As a tool for analyzing the consequence relationship, classify the following sentences as 'entailment', 'neutral', or 'contradiction'. +Language: french, acc: 86.40%, prompt: Determine whether the given sentences are related to 'entailment', 'neutral', or 'contradiction'. +Language: arabic, acc: 84.90%, prompt: Based on your role as a reasoning analyst, analyze the relationship between the given sentences and classify them as 'entailment', 'neutral', or 'contradiction'. +Language: arabic, acc: 84.50%, prompt: Evaluate the relationship between given sentences and classify them as 'entailment', 'neutral', or 'contradiction'. +Language: arabic, acc: 87.10%, prompt: Determine if the following sentences are 'entailment', 'neutral', or 'contradiction'. +Language: arabic, acc: 84.60%, prompt: In your role as a tool of reasoning analysis, investigate the relationship between sentences and classify them as 'entailment', 'neutral', or 'contradiction'. +Language: arabic, acc: 85.10%, prompt: Classify the relationship between the following sentences as 'entailment', 'neutral', or 'contradiction'. +Language: arabic, acc: 84.20%, prompt: In your role as a tool of reasoning analysis, evaluate the relationship between the given sentences and classify them as 'entailment', 'neutral', or 'contradiction'. +Language: arabic, acc: 85.70%, prompt: Analyze the relationship between the given sentences and determine if they are 'entailment', 'neutral', or 'contradiction'. +Language: arabic, acc: 85.60%, prompt: Evaluate the relationship between the following sentences and classify them as 'entailment', 'neutral', or 'contradiction'. +Language: arabic, acc: 85.20%, prompt: In your role as a tool of reasoning analysis, the following sentences are classified as 'entailment', 'neutral', or 'contradiction'. +Language: arabic, acc: 86.50%, prompt: Determine if the sentences given are 'entailment', 'neutral', or 'contradiction'. +Language: spanish, acc: 84.20%, prompt: In your role as an implication analysis tool, evaluate the relationship between the given phrases and classify them as 'entailment', 'neutral', or 'contradiction'. +Language: spanish, acc: 84.40%, prompt: Determine whether there is 'entailment', 'neutral', or 'contradiction' between the sentences given, using this text analysis tool, +Language: spanish, acc: 84.40%, prompt: Analyze the relationship between the two sentences and classify it as 'entailment', 'neutral', or 'contradiction' using this text classification tool, +Language: spanish, acc: 84.90%, prompt: Using this implication analysis tool, decide whether the sentences given are related by 'entailment', 'neutral', or 'contradiction'. +Language: spanish, acc: 84.30%, prompt: Classifies the relationship between the given phrases as 'entailment', 'neutral', or 'contradiction' using this text analysis tool, +Language: spanish, acc: 83.50%, prompt: Evaluate whether there is 'entailment', 'neutral', or 'contradiction' between the sentences provided using this text classification tool, +Language: spanish, acc: 85.00%, prompt: Using this implication analysis tool, decide whether the two sentences are related by 'entailment', 'neutral', or 'contradiction'. +Language: spanish, acc: 84.80%, prompt: Determine whether the given phrases are related by 'entailment', 'neutral', or 'contradiction' using this text analysis tool, +Language: spanish, acc: 84.60%, prompt: Analyze the relationship between the two sentences and classify it as 'entailment', 'neutral', or 'contradiction' using this text analysis tool, +Language: spanish, acc: 84.50%, prompt: Using this text classification tool, it classifies the relationship between the given phrases as 'entailment', 'neutral', or 'contradiction'. +Language: japanese, acc: 84.40%, prompt: As your role as an implication analysis tool, evaluate the relationship of a given sentence and classify it as 'entailment', 'neutral', or 'contradiction'. +Language: japanese, acc: 84.20%, prompt: Use the implication analysis tool as your role to evaluate the relationship of a given sentence and classify it as 'entailment', 'neutral', or 'contradiction'. +Language: japanese, acc: 84.60%, prompt: Use this text classification tool to categorize relationships in a given text as 'entailment', 'neutral', or 'contradiction'. +Language: japanese, acc: 83.80%, prompt: Use the implication analysis tool as your role and classify the relationship of a given sentence as 'entailment', 'neutral', or 'contradiction'. +Language: japanese, acc: 84.50%, prompt: Evaluate the relationship of a given sentence and use this text classification tool to classify it as 'entailment', 'neutral', or 'contradiction'. +Language: japanese, acc: 84.40%, prompt: Evaluate the relationship of a given sentence and use this text classification tool to accurately classify it as 'entailment', 'neutral', or 'contradiction'. +Language: japanese, acc: 83.40%, prompt: Use the implication analysis tool as your role and use this text classification tool to classify the relationship of a given sentence as 'entailment', 'neutral', or 'contradiction'. +Language: japanese, acc: 84.20%, prompt: Use this text classification tool to evaluate the relationship of a given sentence and classify it as 'entailment', 'neutral', or 'contradiction'. +Language: japanese, acc: 84.10%, prompt: Use the implication analysis tool as your role, evaluate the relationship of a given sentence, and use this text classification tool to classify it as 'entailment', 'neutral', or 'contradiction'. +Language: japanese, acc: 83.90%, prompt: Use the implication analysis tool as your role and categorize the relationship of a given sentence strictly as 'entailment', 'neutral', or 'contradiction' using this text classification tool. +Language: korean, acc: 84.80%, prompt: Analyze the relationships between given sentences and classify them as 'entailment', 'neutral', or 'contradiction'. +Language: korean, acc: 84.60%, prompt: In the text categorization task, identify the relationship between given sentences as one of 'entailment', 'neutral', or 'contradiction'. +Language: korean, acc: 84.50%, prompt: Perform the role of analyzing the relationship between sentences and classifying them as 'entailment', 'neutral', or 'contradiction'. +Language: korean, acc: 84.70%, prompt: Evaluate the relationship between two given sentences, and classify them as 'entailment', 'neutral', or 'contradiction'. +Language: korean, acc: 84.20%, prompt: In the text categorization task, perform the role of classifying relationships between given sentences as 'entailment', 'neutral', or 'contradiction'. +Language: korean, acc: 84.20%, prompt: Judge the associations between sentences, and classify them as 'entailment', 'neutral', or 'contradiction'. +Language: korean, acc: 84.60%, prompt: Analyze the relationship between two given sentences and classify them as 'entailment', 'neutral', or 'contradiction'. +Language: korean, acc: 84.20%, prompt: In the task of text classification, identify the relationships between given sentences as 'entailment', 'neutral', or 'contradiction'. +Language: korean, acc: 84.60%, prompt: Act as an instrument to evaluate the relationships between sentences, and classify them as 'entailment', 'neutral', or 'contradiction'. +Language: korean, acc: 84.10%, prompt: Analyze the associations of two given sentences and classify them as 'entailment', 'neutral', or 'contradiction'. + +# mrpc + +## 10 prompts + +Acc: 87.01%, prompt: Can the given sentences be considered semantically identical? Please reply with 'equivalent' or 'not_equivalent'. +Acc: 86.76%, prompt: Compare the following sentences and determine if they share the same semantic meaning by responding with 'equivalent' or 'not_equivalent'. +Acc: 86.27%, prompt: Do these two sentences have the same underlying meaning? Respond with 'equivalent' or 'not_equivalent'. +Acc: 86.27%, prompt: Please analyze the provided sentences and indicate if their meanings are the same by choosing 'equivalent' or 'not_equivalent'. +Acc: 86.03%, prompt: Are the meanings of the following pair of sentences the same? Answer with 'equivalent' or 'not_equivalent'. +Acc: 85.78%, prompt: Evaluate whether the two provided sentences convey the same meaning by answering 'equivalent' or 'not_equivalent'. +Acc: 85.54%, prompt: Do the meanings of these two statements align? Indicate your answer with 'equivalent' or 'not_equivalent'. +Acc: 85.29%, prompt: Examine the pair of sentences and decide if their meanings are identical by answering with 'equivalent' or 'not_equivalent'. +Acc: 83.82%, prompt: Determine if the meanings of the following sentences are semantically equivalent by responding with 'equivalent' or 'not_equivalent'. +Acc: 83.58%, prompt: Assess if the two given sentences have equivalent meanings by selecting 'equivalent' or 'not_equivalent'. + +Acc: 88.97%, prompt: As a sentence similarity evaluator, analyze the provided sentences and indicate if their meanings are 'equivalent' or 'not_equivalent'. +Acc: 87.50%, prompt: In your capacity as a language analyst, assess the following sentences and classify their similarity as 'equivalent' or 'not_equivalent'. +Acc: 87.50%, prompt: As a textual similarity evaluator, analyze the following pair of sentences and determine if they are semantically 'equivalent' or 'not_equivalent'. +Acc: 87.25%, prompt: In your capacity as a semantic comparison tool, examine the given sentences and decide if their meanings are identical, responding with 'equivalent' or 'not_equivalent'. +Acc: 86.76%, prompt: In the role of a textual comparison specialist, examine the given sentences and decide if they share the same meaning, responding with 'equivalent' or 'not_equivalent'. +Acc: 86.27%, prompt: In your capacity as a semantic assessment tool, evaluate the provided sentences and classify their meanings as 'equivalent' or 'not_equivalent'. +Acc: 86.03%, prompt: As a language comparison expert, examine the given pair of sentences and decide if their meanings align, answering with 'equivalent' or 'not_equivalent'. +Acc: 86.03%, prompt: In the role of a sentence comparison analyst, assess the provided sentences and indicate if they convey the same meaning by selecting 'equivalent' or 'not_equivalent'. +Acc: 85.78%, prompt: As a linguistic comparator, review the following pair of sentences and determine their semantic equivalence by choosing 'equivalent' or 'not_equivalent'. +Acc: 85.29%, prompt: As a semantic comparison expert, evaluate the given pair of sentences and determine if they are 'equivalent' or 'not_equivalent'. + +## bertattack + +Original prompt: Can the given sentences be considered semantically identical? Please reply with 'equivalent' or 'not_equivalent'. +Attacked prompt: b"can the related sentences be both semantically inferior? should answer with 'equivalent' or 'not_equivalent'. " +Original acc: 87.01%, attacked acc: 64.46%, dropped acc: 22.55% + +Original prompt: Compare the following sentences and determine if they share the same semantic meaning by responding with 'equivalent' or 'not_equivalent'. +Attacked prompt: b"like the following sentences and determine if they lack the same plural meaning by responding with 'equivalent' or 'not_equivalent'. " +Original acc: 86.76%, attacked acc: 39.71%, dropped acc: 47.06% + +Original prompt: Do these two sentences have the same underlying meaning? Respond with 'equivalent' or 'not_equivalent'. +Attacked prompt: b"don these two sentences have the same associated context? Respond with 'equivalent' or 'not_equivalent'. " +Original acc: 86.27%, attacked acc: 84.31%, dropped acc: 1.96% + +Original prompt: As a sentence similarity evaluator, analyze the provided sentences and indicate if their meanings are 'equivalent' or 'not_equivalent'. +Attacked prompt: b"As a sentence compare evaluators, view the derived variables and indicate if their meanings are 'equivalent' or 'not_equivalent'. " +Original acc: 88.97%, attacked acc: 81.37%, dropped acc: 7.60% + +Original prompt: In your capacity as a language analyst, assess the following sentences and classify their similarity as 'equivalent' or 'not_equivalent'. +Attacked prompt: b"In your capacity as a language analytic, evaluate the two sentences and see their difference as 'equivalent' or 'not_equivalent'. " +Original acc: 87.50%, attacked acc: 82.11%, dropped acc: 5.39% + +Original prompt: As a textual similarity evaluator, analyze the following pair of sentences and determine if they are semantically 'equivalent' or 'not_equivalent'. +Attacked prompt: b"As a case distinction evaluator, analyze the following combining of grammatical and determine if they are semantically 'equivalent' or 'not_equivalent'. " +Original acc: 87.50%, attacked acc: 81.37%, dropped acc: 6.13% + +## checklist + +Original prompt: Can the given sentences be considered semantically identical? Please reply with 'equivalent' or 'not_equivalent'. +Attacked prompt: b"Can the given sentences be considered semantically identical? Please reply with 'equivalent' or 'not_equivalent' zexKUTWJYG. " +Original acc: 87.01%, attacked acc: 86.52%, dropped acc: 0.49% + +Original prompt: Compare the following sentences and determine if they share the same semantic meaning by responding with 'equivalent' or 'not_equivalent'. +Attacked prompt: b"Compare the following sentences and determine if they share the same semantic meaning by responding with 'equivalent' or 'not_equivalent' BWmsLx8xOA. " +Original acc: 86.76%, attacked acc: 86.52%, dropped acc: 0.25% + +Original prompt: Do these two sentences have the same underlying meaning? Respond with 'equivalent' or 'not_equivalent'. +Attacked prompt: b"Do these two sentences have the same underlying meaning? Respond with 'equivalent' or 'not_equivalent' 6a4Yn3RGVc. " +Original acc: 86.27%, attacked acc: 85.78%, dropped acc: 0.49% + +Original prompt: As a sentence similarity evaluator, analyze the provided sentences and indicate if their meanings are 'equivalent' or 'not_equivalent'. +Attacked prompt: b"As a sentence similarity evaluator, analyze the provided sentences and indicate if their meanings are 'equivalent' or 'not_equivalent' XStsD2pUzu. " +Original acc: 88.97%, attacked acc: 88.73%, dropped acc: 0.25% + +Original prompt: In your capacity as a language analyst, assess the following sentences and classify their similarity as 'equivalent' or 'not_equivalent'. +Attacked prompt: b"In your capacity as a language analyst, assess the following sentences and classify their similarity as 'equivalent' or 'not_equivalent' 9vGXgnbWB8. " +Original acc: 87.50%, attacked acc: 87.50%, dropped acc: 0.00% + +Original prompt: As a textual similarity evaluator, analyze the following pair of sentences and determine if they are semantically 'equivalent' or 'not_equivalent'. +Attacked prompt: b"As a textual similarity evaluator, analyze the following pair of sentences and determine if they are semantically 'equivalent' or 'not_equivalent' ofw9fEkN5R. " +Original acc: 87.50%, attacked acc: 87.25%, dropped acc: 0.25% + +## deepwordbug + +Original prompt: Can the given sentences be considered semantically identical? Please reply with 'equivalent' or 'not_equivalent'. +Attacked prompt: b"Can the given sentences be considered semantically idrntical? Please reply with 'equivalent' or 'not_equivalent'. " +Original acc: 87.01%, attacked acc: 84.31%, dropped acc: 2.70% + +Original prompt: Compare the following sentences and determine if they share the same semantic meaning by responding with 'equivalent' or 'not_equivalent'. +Attacked prompt: b"Compare the following senteces and determine if they sharSe the same semantic meaniCg by responding with 'equivalent' or 'not_equivalent'. " +Original acc: 86.76%, attacked acc: 85.29%, dropped acc: 1.47% + +Original prompt: Do these two sentences have the same underlying meaning? Respond with 'equivalent' or 'not_equivalent'. +Attacked prompt: b"Do these two seRtences have the same underlying mFeaning? Respond with 'equivalent' or 'not_equivalent'. " +Original acc: 86.27%, attacked acc: 85.29%, dropped acc: 0.98% + +Original prompt: As a sentence similarity evaluator, analyze the provided sentences and indicate if their meanings are 'equivalent' or 'not_equivalent'. +Attacked prompt: b"As a sentence siimlarity evaluator, anawyze the providBed sentences and indicate if their meanCings are 'equivalent' or 'not_equivalent'. " +Original acc: 88.97%, attacked acc: 84.80%, dropped acc: 4.17% + +Original prompt: In your capacity as a language analyst, assess the following sentences and classify their similarity as 'equivalent' or 'not_equivalent'. +Attacked prompt: b"In your capacity as a language analyst, assess the following sentences and classify their similarity as 'equivalent' or 'not_equivalent'. " +Original acc: 87.50%, attacked acc: 87.50%, dropped acc: 1.47% + +Original prompt: As a textual similarity evaluator, analyze the following pair of sentences and determine if they are semantically 'equivalent' or 'not_equivalent'. +Attacked prompt: b"As a extual simialrity evaluator, analyze the following pair of sentences and determine if they are semantically 'equivalent' or 'not_equivalent'. " +Original acc: 87.50%, attacked acc: 84.56%, dropped acc: 2.94% + +## stresstest + +Original prompt: Can the given sentences be considered semantically identical? Please reply with 'equivalent' or 'not_equivalent'. +Attacked prompt: b"Can the given sentences be considered semantically identical? Please reply with 'equivalent' or 'not_equivalent' and false is not true . " +Original acc: 87.01%, attacked acc: 86.52%, dropped acc: 0.49% + +Original prompt: Compare the following sentences and determine if they share the same semantic meaning by responding with 'equivalent' or 'not_equivalent'. +Attacked prompt: b"Compare the following sentences and determine if they share the same semantic meaning by responding with 'equivalent' or 'not_equivalent' and false is not true . " +Original acc: 86.76%, attacked acc: 85.78%, dropped acc: 0.98% + +Original prompt: Do these two sentences have the same underlying meaning? Respond with 'equivalent' or 'not_equivalent'. +Attacked prompt: b"Do these two sentences have the same underlying meaning? Respond with 'equivalent' or 'not_equivalent' and false is not true . " +Original acc: 86.27%, attacked acc: 85.78%, dropped acc: 0.49% + +Original prompt: As a sentence similarity evaluator, analyze the provided sentences and indicate if their meanings are 'equivalent' or 'not_equivalent'. +Attacked prompt: b"As a sentence similarity evaluator, analyze the provided sentences and indicate if their meanings are 'equivalent' or 'not_equivalent' and true is true and true is true and true is true and true is true and true is true . " +Original acc: 88.97%, attacked acc: 87.75%, dropped acc: 1.23% + +Original prompt: In your capacity as a language analyst, assess the following sentences and classify their similarity as 'equivalent' or 'not_equivalent'. +Attacked prompt: b"In your capacity as a language analyst, assess the following sentences and classify their similarity as 'equivalent' or 'not_equivalent' and false is not true . " +Original acc: 87.50%, attacked acc: 87.25%, dropped acc: 0.25% + +Original prompt: As a textual similarity evaluator, analyze the following pair of sentences and determine if they are semantically 'equivalent' or 'not_equivalent'. +Attacked prompt: b"As a textual similarity evaluator, analyze the following pair of sentences and determine if they are semantically 'equivalent' or 'not_equivalent' and false is not true . " +Original acc: 87.50%, attacked acc: 87.01%, dropped acc: 0.49% + +## textbugger + +Original prompt: Can the given sentences be considered semantically identical? Please reply with 'equivalent' or 'not_equivalent'. +Attacked prompt: b"Can the given sentences be deemed semantically idntical? Please reply with 'equivalent' or 'not_equivalent'. " +Original acc: 87.01%, attacked acc: 83.82%, dropped acc: 3.19% + +Original prompt: Compare the following sentences and determine if they share the same semantic meaning by responding with 'equivalent' or 'not_equivalent'. +Attacked prompt: b"Compare the later sentences and determine if they share the same semnatic meannig by responding with 'equivalent' or 'not_equivalent'. " +Original acc: 86.76%, attacked acc: 84.80%, dropped acc: 1.96% + +Original prompt: Do these two sentences have the same underlying meaning? Respond with 'equivalent' or 'not_equivalent'. +Attacked prompt: b"Do these two verdicts have the same underlying meaning? Respond with 'equivalent' or 'not_equivalent'. " +Original acc: 86.27%, attacked acc: 85.05%, dropped acc: 1.23% + +Original prompt: As a sentence similarity evaluator, analyze the provided sentences and indicate if their meanings are 'equivalent' or 'not_equivalent'. +Attacked prompt: b"Since a sentence sim ilarity evaluator, analyze the gave sentences and indicate if their meanings are 'equivalent' or 'not_equivalent'. " +Original acc: 88.97%, attacked acc: 85.54%, dropped acc: 3.43% + +Original prompt: In your capacity as a language analyst, assess the following sentences and classify their similarity as 'equivalent' or 'not_equivalent'. +Attacked prompt: b"In your capacity as a language \xc9\x91nalyst, assess the following sentenes and classify their metaphor as 'equivalent' or 'not_equivalent'. " +Original acc: 87.50%, attacked acc: 83.58%, dropped acc: 3.92% + +Original prompt: As a textual similarity evaluator, analyze the following pair of sentences and determine if they are semantically 'equivalent' or 'not_equivalent'. +Attacked prompt: b"Since a t\xd0\xb5xtual portrait evaluator, analyze the following pai\xe2\xb2\x85 of sentences and determine if they are semantically 'equivalent' or 'not_equivalent'. " +Original acc: 87.50%, attacked acc: 84.31%, dropped acc: 3.19% + +## textfooler + +Original prompt: Can the given sentences be considered semantically identical? Please reply with 'equivalent' or 'not_equivalent'. +Attacked prompt: b"Can the given sentences be dealt semantically equivalent? Prayed reply with 'equivalent' or 'not_equivalent'. " +Original acc: 87.01%, attacked acc: 84.31%, dropped acc: 2.70% + +Original prompt: Compare the following sentences and determine if they share the same semantic meaning by responding with 'equivalent' or 'not_equivalent'. +Attacked prompt: b"Compare the later judgements and defines if they exchange the same semantic sensation by answered with 'equivalent' or 'not_equivalent'. " +Original acc: 86.52%, attacked acc: 83.58%, dropped acc: 2.94% + +Original prompt: Do these two sentences have the same underlying meaning? Respond with 'equivalent' or 'not_equivalent'. +Attacked prompt: b"Do these two judging am the same underlying meaning? Answer with 'equivalent' or 'not_equivalent'. " +Original acc: 86.27%, attacked acc: 84.56%, dropped acc: 1.72% + +Original prompt: As a sentence similarity evaluator, analyze the provided sentences and indicate if their meanings are 'equivalent' or 'not_equivalent'. +Attacked prompt: b"As a sentence metaphor evaluator, analyze the brought priors and demonstrating if their meanings are 'equivalent' or 'not_equivalent'. " +Original acc: 89.22%, attacked acc: 85.29%, dropped acc: 3.92% + +Original prompt: As a textual similarity evaluator, analyze the following pair of sentences and determine if they are semantically 'equivalent' or 'not_equivalent'. +Attacked prompt: b"As a textual similarity evaluator, analyze the following pair of sentences and determine if they are semantically 'equivalent' or 'not_equivalent'. " +Original acc: 87.75%, attacked acc: 87.75%, dropped acc: 1.47% + +Original prompt: In your capacity as a language analyst, assess the following sentences and classify their similarity as 'equivalent' or 'not_equivalent'. +Attacked prompt: b"In your capacity as a language analyst, assess the following sentence and classify their portrait as 'equivalent' or 'not_equivalent'. " +Original acc: 87.50%, attacked acc: 85.29%, dropped acc: 2.21% + +## translation + +Language: chinese, acc: 85.54%, prompt: As an expert in semantic comparison, evaluates two given sentences to determine whether they are 'equivalent' or 'not_equivalent'. +Language: chinese, acc: 85.54%, prompt: From the point of view of semantic comparison, determine whether this pair of sentences is 'equivalent' or 'not_equivalent'. +Language: chinese, acc: 85.29%, prompt: Using the semantic comparison method, determine whether the following two statements are 'equivalent' or 'not_equivalent'. +Language: chinese, acc: 85.05%, prompt: For the following two sentences, determine whether they are 'equivalent' or 'not_equivalent' based on semantic comparison. +Language: chinese, acc: 85.29%, prompt: As an expert in semantic comparison, please evaluate the following two sentences and determine if they are 'equivalent' or 'not_equivalent'. +Language: chinese, acc: 86.03%, prompt: Using semantic comparison techniques, determine whether the following two sentences are 'equivalent' or 'not_equivalent'. +Language: chinese, acc: 85.29%, prompt: Please determine whether the following two sentences are 'equivalent' or 'not_equivalent' according to the standard of semantic comparison. +Language: chinese, acc: 85.05%, prompt: As an expert in the field of semantic comparison, please evaluate the following two sentences and determine whether they are 'equivalent' or 'not_equivalent'. +Language: chinese, acc: 85.54%, prompt: Using semantic comparison, determine whether the following two sentences are 'equivalent' or 'not_equivalent'. +Language: chinese, acc: 85.05%, prompt: Determine whether the following two sentences are 'equivalent' or 'not_equivalent' based on semantic comparison. +Language: french, acc: 84.80%, prompt: As an expert in semantic comparison, evaluate the following pair of sentences and determine whether they are 'equivalent' or 'not_equivalent'. +Language: french, acc: 84.80%, prompt: Can you determine whether the following two sentences are 'equivalent' or 'not_equivalent' as a semantic comparison expert? +Language: french, acc: 85.29%, prompt: Using your expertise in semantic comparison, determine whether the following two sentences are 'equivalent' or 'not_equivalent'. +Language: french, acc: 87.50%, prompt: As a semantic comparison specialist, assess the similarity between the following two sentences and determine whether they are 'equivalent' or 'not_equivalent'. +Language: french, acc: 84.80%, prompt: Are you able to determine whether the following two sentences are 'equivalent' or 'not_equivalent' as an expert in semantic comparison? +Language: french, acc: 85.29%, prompt: As a semantic comparison professional, evaluate the following pair of sentences and indicate whether they are 'equivalent' or 'not_equivalent'. +Language: french, acc: 85.54%, prompt: Can you determine whether the following two sentences have a 'equivalent' or 'not_equivalent' meaning as an expert in semantic comparison? +Language: french, acc: 87.75%, prompt: As an expert in semantic comparison, assess the similarity between the following two sentences and determine whether they are 'equivalent' or 'not_equivalent'. +Language: french, acc: 85.29%, prompt: Using your expertise in semantic comparison, determine whether the following two sentences are 'equivalent' or 'not_equivalent' in terms of meaning. +Language: french, acc: 87.75%, prompt: As a semantic comparison professional, assess the similarity between the following two sentences and indicate whether they are 'equivalent' or 'not_equivalent'. +Language: arabic, acc: 85.05%, prompt: As an expert in semantic comparison, evaluate the two given sentences and determine whether they are 'equivalent' or 'not_equivalent'. +Language: arabic, acc: 86.76%, prompt: Based on my experience in semantic analysis, classify the following two sentences as 'equivalent' or 'not_equivalent'. +Language: arabic, acc: 85.29%, prompt: As an expert in semantic comparison, analyze the following two sentences and classify them as 'equivalent' or 'not_equivalent'. +Language: arabic, acc: 85.29%, prompt: Your task as an expert in semantic comparison is to evaluate the following two sentences and determine whether they are 'equivalent' or 'not_equivalent'. +Language: arabic, acc: 86.03%, prompt: As a semantic comparison specialist, analyze the two data statements and insert them into one of the following categories: 'equivalent' or 'not_equivalent'. +Language: arabic, acc: 85.78%, prompt: Based on my experience in semantic analysis, classify the following two sentences between 'equivalent' or 'not_equivalent'. +Language: arabic, acc: 84.80%, prompt: Your role as a semantic comparison specialist requires analyzing the two given sentences and determining whether they are 'equivalent' or 'not_equivalent'. +Language: arabic, acc: 86.76%, prompt: As an experienced semantic analyst, classify the following two sentences as 'equivalent' or 'not_equivalent'. +Language: arabic, acc: 85.54%, prompt: Your job as a semantic analyst evaluates the following two sentences as 'equivalent' or 'not_equivalent'. +Language: arabic, acc: 85.78%, prompt: As a semantic analyst, determine whether the given sentences are 'equivalent' or 'not_equivalent' based on their relationship. +Language: spanish, acc: 84.80%, prompt: As an expert in semantic comparison, it evaluates the pair of sentences provided and determines whether they are 'equivalent' or 'not_equivalent'. +Language: spanish, acc: 86.76%, prompt: Based on my experience in semantic analysis, classify the following two sentences as 'equivalent' or 'not_equivalent'. +Language: spanish, acc: 85.54%, prompt: As an expert in semantic comparison, analyze the two sentences given and classify them as 'equivalent' or 'not_equivalent'. +Language: spanish, acc: 84.80%, prompt: Your task as a semantic comparison specialist is to evaluate the following two sentences and determine whether they are 'equivalent' or 'not_equivalent'. +Language: spanish, acc: 85.78%, prompt: As an expert in semantic analysis, he makes a classification of the following two sentences based on their 'equivalent' or 'not_equivalent'. +Language: spanish, acc: 85.29%, prompt: Based on your experience of semantic comparison, classify the next two sentences as 'equivalent' or 'not_equivalent'. +Language: spanish, acc: 86.27%, prompt: As a specialist in semantic analysis, you are given the task of analysing the two sentences given and classifying them as 'equivalent' or 'not_equivalent'. +Language: spanish, acc: 85.05%, prompt: As an expert in semantic comparison, he classifies the following two sentences into 'equivalent' or 'not_equivalent'. +Language: spanish, acc: 86.27%, prompt: As a specialist in semantic analysis, evaluate the following two sentences and classify them as 'equivalent' or 'not_equivalent'. +Language: spanish, acc: 85.78%, prompt: Your task as an expert in semantic comparison is to analyze the two sentences provided and determine whether they are 'equivalent' or 'not_equivalent' based on their semantic relationship. +Language: japanese, acc: 84.80%, prompt: Evaluate whether a given pair of sentences is 'equivalent' or 'not_equivalent', depending on the context. +Language: japanese, acc: 85.29%, prompt: Use a semantic comparison to determine whether a given pair of sentences is 'equivalent' or 'not_equivalent'. +Language: japanese, acc: 85.78%, prompt: Evaluate a given pair of sentences as 'equivalent' or 'not_equivalent' by determining whether they have the same semantic meaning. +Language: japanese, acc: 85.78%, prompt: Determine whether a given pair of sentences is synonyms and evaluate whether they are 'equivalent' or 'not_equivalent'. +Language: japanese, acc: 85.54%, prompt: Determine whether a given pair of sentences is 'equivalent' or 'not_equivalent', and whether they are semantically identical. +Language: japanese, acc: 85.29%, prompt: Determinate whether a given pair of sentences has the same meaning and evaluate whether they are 'equivalent' or 'not_equivalent'. +Language: japanese, acc: 85.78%, prompt: Evaluate whether a given pair of sentences is 'equivalent' or 'not_equivalent' by determining whether they are semantically identical. +Language: japanese, acc: 85.05%, prompt: Judge whether a given pair of sentences is equal and evaluate whether they are 'equivalent' or 'not_equivalent'. +Language: japanese, acc: 85.54%, prompt: Determinate whether a given pair of sentences are semantically equal and evaluate whether they are 'equivalent' or 'not_equivalent'. +Language: japanese, acc: 84.07%, prompt: Whether a given pair of sentences is 'equivalent' or 'not_equivalent' depends on the context. +Language: korean, acc: 85.29%, prompt: As a sentence comparator, evaluate the two sentences given to determine 'equivalent' or 'not_equivalent'. +Language: korean, acc: 86.03%, prompt: Compare two sentences to determine 'equivalent' or 'not_equivalent'. For this you need qualifications as a specialist in semantic comparison. +Language: korean, acc: 85.29%, prompt: It takes your knowledge as an expert in semantic comparison to determine that two sentences are 'equivalent' or 'not_equivalent'. +Language: korean, acc: 85.05%, prompt: As a specialist in semantic comparison, evaluate whether two given sentences are 'equivalent' or 'not_equivalent'. +Language: korean, acc: 85.54%, prompt: Analyze two sentences to determine 'equivalent' or 'not_equivalent'. For that you need the knowledge of a semantic comparison expert. +Language: korean, acc: 85.78%, prompt: As an expert in semantic comparison, decide whether two sentences are 'equivalent' or 'not_equivalent'. +Language: korean, acc: 85.05%, prompt: It takes the knowledge of an expert in semantic comparison to compare two sentences to judge 'equivalent' or 'not_equivalent'. +Language: korean, acc: 84.80%, prompt: Experience as an expert in semantic comparison is required to determine whether two given sentences are 'equivalent' or 'not_equivalent'. +Language: korean, acc: 85.29%, prompt: As an expert in semantic comparison, determine whether two sentences are 'equivalent' or 'not_equivalent'. +Language: korean, acc: 85.78%, prompt: Analyze two sentences to determine 'equivalent' or 'not_equivalent'. For this, you need a qualification as a specialist in semantic comparison. + +# qnli + +## 10 prompts + +Acc: 94.50%, prompt: Based on the provided context and question, decide if the information supports the answer by responding with 'entailment' or 'not_entailment'. +Acc: 94.00%, prompt: Analyze the context and question, and indicate if the context entails the answer by choosing 'entailment' or 'not_entailment'. +Acc: 94.00%, prompt: Review the given context and question, and decide if the context contains enough information to support the answer by selecting 'entailment' or 'not_entailment'. +Acc: 93.90%, prompt: Evaluate whether the given context supports the answer to the question by responding with 'entailment' or 'not_entailment'. +Acc: 93.70%, prompt: Based on the information in the context, decide if the answer to the question is justified by choosing 'entailment' or 'not_entailment'. +Acc: 93.50%, prompt: Given the question and context provided, determine if the answer can be inferred by choosing 'entailment' or 'not_entailment'. +Acc: 93.50%, prompt: Examine the context and question, and determine if the context logically implies the answer by selecting 'entailment' or 'not_entailment'. +Acc: 93.20%, prompt: Please assess if the answer to the question can be derived from the given context by selecting 'entailment' or 'not_entailment'. +Acc: 93.00%, prompt: Consider the context and question, and indicate if the answer can be logically deduced from the context by responding with 'entailment' or 'not_entailment'. +Acc: 93.00%, prompt: Assess if the answer to the question can be logically concluded from the provided context by choosing 'entailment' or 'not_entailment'. + +Acc: 93.90%, prompt: As a semantic researcher, evaluate whether the provided context supports the answer to the question and choose 'entailment' or 'not_entailment'. +Acc: 93.70%, prompt: In your role as a semantic evaluator, determine if the provided context justifies the answer to the question and answer with 'entailment' or 'not_entailment'. +Acc: 93.70%, prompt: As a semantic interpreter, assess whether the provided context supports the answer to the given question and answer with 'entailment' or 'not_entailment'. +Acc: 93.50%, prompt: In the capacity of a language evaluator, examine if the given context justifies the answer to the question and indicate your assessment with 'entailment' or 'not_entailment'. +Acc: 93.40%, prompt: As a language expert, assess if the given context entails the answer to the question and respond with 'entailment' or 'not_entailment'. +Acc: 93.30%, prompt: As a textual analyst, examine if the given context logically implies the answer to the question and indicate your decision with 'entailment' or 'not_entailment'. +Acc: 93.30%, prompt: In your role as a linguistic investigator, determine if the context given entails the answer to the question and provide your conclusion with 'entailment' or 'not_entailment'. +Acc: 93.20%, prompt: In the capacity of a language specialist, decide if the context presented contains enough information to infer the answer to the question and respond with 'entailment' or 'not_entailment'. +Acc: 93.00%, prompt: As a textual inference expert, analyze if the answer to the question can be deduced from the provided context and select 'entailment' or 'not_entailment'. +Acc: 92.90%, prompt: As a linguistic consultant, decide if the answer to the question is logically supported by the provided context and respond with 'entailment' or 'not_entailment'. + +## bertattack + +Original prompt: Based on the provided context and question, decide if the information supports the answer by responding with 'entailment' or 'not_entailment'. +Attacked prompt: b"Based on the provided context and knowledge, then if the form permits the answer by responses with 'entailment' or 'not_entailment'. " +Original acc: 94.50%, attacked acc: 92.20%, dropped acc: 2.30% + +Original prompt: Analyze the context and question, and indicate if the context entails the answer by choosing 'entailment' or 'not_entailment'. +Attacked prompt: b"Analyze the context and question, and indicate if the dictionary ennotes the context by avoiding 'entailment' or 'not_entailment'. " +Original acc: 94.00%, attacked acc: 88.80%, dropped acc: 5.20% + +Original prompt: Review the given context and question, and decide if the context contains enough information to support the answer by selecting 'entailment' or 'not_entailment'. +Attacked prompt: b"review the requested sentence and question, and do if the context contains enough information to further the asking by selecting 'entailment' or 'not_entailment'. " +Original acc: 94.00%, attacked acc: 92.60%, dropped acc: 1.40% + +Original prompt: As a semantic researcher, evaluate whether the provided context supports the answer to the question and choose 'entailment' or 'not_entailment'. +Attacked prompt: b"are a semantic analysis, evaluate assuming the provided context supports the answers to the answer and reject 'entailment' or 'not_entailment'. " +Original acc: 93.90%, attacked acc: 90.20%, dropped acc: 3.70% + +Original prompt: In your role as a semantic evaluator, determine if the provided context justifies the answer to the question and answer with 'entailment' or 'not_entailment'. +Attacked prompt: b"if your performance as a semantic evaual-, assess if the provided context justifies the answer to the question and answer with 'entailment' or 'not_entailment'. " +Original acc: 93.60%, attacked acc: 92.70%, dropped acc: 0.90% + +Original prompt: As a semantic interpreter, assess whether the provided context supports the answer to the given question and answer with 'entailment' or 'not_entailment'. +Attacked prompt: b"with a semantic presentation, evaluation why the provided contexts supports the answer to the given answer and questions with 'entailment' or 'not_entailment'. " +Original acc: 93.60%, attacked acc: 83.50%, dropped acc: 10.10% + +## checklist + +Original prompt: Based on the provided context and question, decide if the information supports the answer by responding with 'entailment' or 'not_entailment'. +Attacked prompt: b"Based on the provided context and question, decide if the information supports the answer by responding with 'entailment' or 'not_entailment' EAB4KP2NVY. " +Original acc: 94.50%, attacked acc: 94.20%, dropped acc: 0.30% + +Original prompt: Analyze the context and question, and indicate if the context entails the answer by choosing 'entailment' or 'not_entailment'. +Attacked prompt: b"Analyze the context and question, and indicate if the context entails the answer by choosing 'entailment' or 'not_entailment' lf8wBa2yEm. " +Original acc: 94.00%, attacked acc: 93.40%, dropped acc: 0.60% + +Original prompt: Review the given context and question, and decide if the context contains enough information to support the answer by selecting 'entailment' or 'not_entailment'. +Attacked prompt: b"Review the given context and question, and decide if the context contains enough information to support the answer by selecting 'entailment' or 'not_entailment' SFPCqpiClT. " +Original acc: 94.00%, attacked acc: 93.70%, dropped acc: 0.30% + +Original prompt: As a semantic researcher, evaluate whether the provided context supports the answer to the question and choose 'entailment' or 'not_entailment'. +Attacked prompt: b"As a semantic researcher, evaluate whether the provided context supports the answer to the question and choose 'entailment' or 'not_entailment' AMsRIKZniY. " +Original acc: 93.90%, attacked acc: 93.60%, dropped acc: 0.30% + +Original prompt: In your role as a semantic evaluator, determine if the provided context justifies the answer to the question and answer with 'entailment' or 'not_entailment'. +Attacked prompt: b"In your role as a semantic evaluator, determine if the provided context justifies the answer to the question and answer with 'entailment' or 'not_entailment' zq0DcZ5dnI. " +Original acc: 93.70%, attacked acc: 93.50%, dropped acc: 0.20% + +Original prompt: As a semantic interpreter, assess whether the provided context supports the answer to the given question and answer with 'entailment' or 'not_entailment'. +Attacked prompt: b"As a semantic interpreter, assess whether the provided context supports the answer to the given question and answer with 'entailment' or 'not_entailment' 9vGXgnbWB8. " +Original acc: 93.70%, attacked acc: 93.60%, dropped acc: 0.10% + +## deepwordbug + +Original prompt: Based on the provided context and question, decide if the information supports the answer by responding with 'entailment' or 'not_entailment'. +Attacked prompt: b"Based on the provided context and questJon, decide if the informaton supforts the answer by responding with 'entailment' or 'not_entailment'. " +Original acc: 94.50%, attacked acc: 93.90%, dropped acc: 0.60% + +Original prompt: Analyze the context and question, and indicate if the context entails the answer by choosing 'entailment' or 'not_entailment'. +Attacked prompt: b"Analyze the context and question, and indicate if the context entails the answer by choosing 'entailment' or 'not_entailment'. " +Original acc: 94.00%, attacked acc: 94.00%, dropped acc: 0.50% + +Original prompt: Review the given context and question, and decide if the context contains enough information to support the answer by selecting 'entailment' or 'not_entailment'. +Attacked prompt: b"Review the given cotext and question, and Pdecide if the context contains enough information to sGupport the answe by sefecting 'entailment' or 'not_entailment'. " +Original acc: 94.00%, attacked acc: 93.40%, dropped acc: 0.60% + +Original prompt: As a semantic researcher, evaluate whether the provided context supports the answer to the question and choose 'entailment' or 'not_entailment'. +Attacked prompt: b"As a seantic researcher, evaluate hether the provided context suports the answer to the question and ahoose 'entailment' or 'not_entailment'. " +Original acc: 93.90%, attacked acc: 93.10%, dropped acc: 0.80% + +Original prompt: In your role as a semantic evaluator, determine if the provided context justifies the answer to the question and answer with 'entailment' or 'not_entailment'. +Attacked prompt: b"In your role as a Pemantic evaluaztor, determine if the provided context justifies the answer to the question and answer with 'entailment' or 'not_entailment'. " +Original acc: 93.70%, attacked acc: 93.20%, dropped acc: 0.50% + +Original prompt: As a semantic interpreter, assess whether the provided context supports the answer to the given question and answer with 'entailment' or 'not_entailment'. +Attacked prompt: b"As a semantic interpreter, assless wether the provided context supports the answer to the given question and answer with 'entailment' or 'not_entailment'. " +Original acc: 93.70%, attacked acc: 92.90%, dropped acc: 0.80% + +## stresstest + +Original prompt: Based on the provided context and question, decide if the information supports the answer by responding with 'entailment' or 'not_entailment'. +Attacked prompt: b"Based on the provided context and question, decide if the information supports the answer by responding with 'entailment' or 'not_entailment' and false is not true . " +Original acc: 94.50%, attacked acc: 94.60%, dropped acc: -0.10% + +Original prompt: Analyze the context and question, and indicate if the context entails the answer by choosing 'entailment' or 'not_entailment'. +Attacked prompt: b"Analyze the context and question, and indicate if the context entails the answer by choosing 'entailment' or 'not_entailment' and true is true and true is true and true is true and true is true and true is true . " +Original acc: 94.00%, attacked acc: 93.90%, dropped acc: 0.10% + +Original prompt: Review the given context and question, and decide if the context contains enough information to support the answer by selecting 'entailment' or 'not_entailment'. +Attacked prompt: b"Review the given context and question, and decide if the context contains enough information to support the answer by selecting 'entailment' or 'not_entailment' and false is not true . " +Original acc: 94.00%, attacked acc: 94.30%, dropped acc: -0.30% + +Original prompt: As a semantic researcher, evaluate whether the provided context supports the answer to the question and choose 'entailment' or 'not_entailment'. +Attacked prompt: b"As a semantic researcher, evaluate whether the provided context supports the answer to the question and choose 'entailment' or 'not_entailment' and true is true . " +Original acc: 93.90%, attacked acc: 94.00%, dropped acc: -0.10% + +Original prompt: In your role as a semantic evaluator, determine if the provided context justifies the answer to the question and answer with 'entailment' or 'not_entailment'. +Attacked prompt: b"In your role as a semantic evaluator, determine if the provided context justifies the answer to the question and answer with 'entailment' or 'not_entailment' and true is true and true is true and true is true and true is true and true is true . " +Original acc: 93.70%, attacked acc: 94.10%, dropped acc: -0.40% + +Original prompt: As a semantic interpreter, assess whether the provided context supports the answer to the given question and answer with 'entailment' or 'not_entailment'. +Attacked prompt: b"As a semantic interpreter, assess whether the provided context supports the answer to the given question and answer with 'entailment' or 'not_entailment' and true is true . " +Original acc: 93.70%, attacked acc: 94.10%, dropped acc: -0.40% + +## textbugger + +Original prompt: Based on the provided context and question, decide if the information supports the answer by responding with 'entailment' or 'not_entailment'. +Attacked prompt: b"Based on the provided context and que\xd1\x95tion, decide if the details supporting the answer by responding with 'entailment' or 'not_entailment'. " +Original acc: 94.50%, attacked acc: 93.80%, dropped acc: 0.70% + +Original prompt: Analyze the context and question, and indicate if the context entails the answer by choosing 'entailment' or 'not_entailment'. +Attacked prompt: b"Analyze the context and question, and indicate if the context implies the answer by choosing 'entailment' or 'not_entailment'. " +Original acc: 94.00%, attacked acc: 93.30%, dropped acc: 0.70% + +Original prompt: Review the given context and question, and decide if the context contains enough information to support the answer by selecting 'entailment' or 'not_entailment'. +Attacked prompt: b"Review the given co\xd5\xb8text and question, and dcide if the context contains enough particulars to support the answe\xe2\xb2\x85 by selecting 'entailment' or 'not_entailment'. " +Original acc: 94.00%, attacked acc: 92.90%, dropped acc: 1.10% + +Original prompt: As a semantic researcher, evaluate whether the provided context supports the answer to the question and choose 'entailment' or 'not_entailment'. +Attacked prompt: b"As a semantic investigator, evalu\xc9\x91te both the p\xe2\xb2\x85ovided context support the answer to the question and choose 'entailment' or 'not_entailment'. " +Original acc: 93.90%, attacked acc: 93.10%, dropped acc: 0.80% + +Original prompt: In your role as a semantic evaluator, determine if the provided context justifies the answer to the question and answer with 'entailment' or 'not_entailment'. +Attacked prompt: b"During your ro le as a semantic ealuator, deter mine if the provided context justifies the answer to the question and answer with 'entailment' or 'not_entailment'. " +Original acc: 93.70%, attacked acc: 92.70%, dropped acc: 1.00% + +Original prompt: As a semantic interpreter, assess whether the provided context supports the answer to the given question and answer with 'entailment' or 'not_entailment'. +Attacked prompt: b"Iike a semantic interpretation, evaluated lf the pr\xd0\xbevided context supports the answer to the given question and answers with 'entailment' or 'not_entailment'. " +Original acc: 93.70%, attacked acc: 92.30%, dropped acc: 1.40% + +## textfooler + +Original prompt: Based on the provided context and question, decide if the information supports the answer by responding with 'entailment' or 'not_entailment'. +Attacked prompt: b"Based on the provided context and question, decide if the particulars brackets the answered by responding with 'entailment' or 'not_entailment'. " +Original acc: 94.60%, attacked acc: 93.30%, dropped acc: 1.30% + +Original prompt: Analyze the context and question, and indicate if the context entails the answer by choosing 'entailment' or 'not_entailment'. +Attacked prompt: b"Explore the context and question, and suggest if the context involves the rebuttal by selected 'entailment' or 'not_entailment'. " +Original acc: 94.00%, attacked acc: 54.20%, dropped acc: 39.80% + +Original prompt: Review the given context and question, and decide if the context contains enough information to support the answer by selecting 'entailment' or 'not_entailment'. +Attacked prompt: b"Scrutinized the given backdrop and theme, and choices if the context composed enough indications to backing the answer by choosing 'entailment' or 'not_entailment'. " +Original acc: 94.00%, attacked acc: 92.30%, dropped acc: 1.70% + +Original prompt: As a semantic researcher, evaluate whether the provided context supports the answer to the question and choose 'entailment' or 'not_entailment'. +Attacked prompt: b"Because a semantic inquisitors, appraise whether the provided context alleges the rebuttal to the issuing and selector 'entailment' or 'not_entailment'. " +Original acc: 93.90%, attacked acc: 61.50%, dropped acc: 32.40% + +Original prompt: In your role as a semantic evaluator, determine if the provided context justifies the answer to the question and answer with 'entailment' or 'not_entailment'. +Attacked prompt: b"In your role as a semantic evaluator, determine if the presented context deserved the rebuttal to the questions and answering with 'entailment' or 'not_entailment'. " +Original acc: 93.60%, attacked acc: 90.50%, dropped acc: 3.10% + +Original prompt: As a semantic interpreter, assess whether the provided context supports the answer to the given question and answer with 'entailment' or 'not_entailment'. +Attacked prompt: b"As a semantic performer, appraised whether the provided framework supports the rebuttal to the supplied question and cope with 'entailment' or 'not_entailment'. " +Original acc: 93.60%, attacked acc: 92.50%, dropped acc: 1.10% + +## translation + +Language: chinese, acc: 93.50%, prompt: Determine whether the answer is implied or not based on the context. Answer 'entailment' or 'not_entailment'. +Language: chinese, acc: 94.30%, prompt: As a language expert, determine whether the text contains the answer and choose 'entailment' or 'not_entailment'. +Language: chinese, acc: 93.70%, prompt: Determine whether the text implies an answer, and select 'entailment' or 'not_entailment'. +Language: chinese, acc: 93.10%, prompt: Given the text and the question, whether the answer is implied, select 'entailment' or 'not_entailment'. +Language: chinese, acc: 94.20%, prompt: Determine whether the text contains the answer, depending on the context. Select 'entailment' or 'not_entailment'. +Language: chinese, acc: 93.80%, prompt: As a language expert, determine whether a text can contain an answer, and say 'entailment' or 'not_entailment'. +Language: chinese, acc: 93.60%, prompt: Please determine whether the text implies an answer. Answer 'entailment' or 'not_entailment'. +Language: chinese, acc: 93.70%, prompt: Please select 'entailment' or 'not_entailment' based on the text and the question. +Language: chinese, acc: 93.20%, prompt: Assess whether the answer is implied based on the context. Answer 'entailment' or 'not_entailment'. +Language: chinese, acc: 94.20%, prompt: Please determine whether the text contains the answer and answer 'entailment' or 'not_entailment'. +Language: french, acc: 93.50%, prompt: As a linguistic expert, assess whether the given context involves the answer to the question and answer with 'entailment' or 'not_entailment'. +Language: french, acc: 94.10%, prompt: Determine whether the information provided in the context necessarily leads to the answer to the question asked and indicate 'entailment' or 'not_entailment'. +Language: french, acc: 93.40%, prompt: Analyze the text to determine if the answer to the question is implied in the context and specify 'entailment' or 'not_entailment'. +Language: french, acc: 93.50%, prompt: Based on the given context, decide whether the answer to the question is necessarily involved and mark 'entailment' or 'not_entailment'. +Language: french, acc: 93.10%, prompt: Evaluate whether the answer to the question can be deduced from the given context and mark 'entailment' or 'not_entailment'. +Language: french, acc: 94.70%, prompt: Discern whether the context provided directly involves the answer to the question and indicate 'entailment' or 'not_entailment'. +Language: french, acc: 93.30%, prompt: Determine if the context contains enough information to involve the answer to the question and mark 'entailment' or 'not_entailment'. +Language: french, acc: 93.60%, prompt: Assess whether the context provided necessarily leads to the answer to the question and answer with 'entailment' or 'not_entailment'. +Language: french, acc: 93.10%, prompt: Analyze the text to determine if the answer to the question is involved in the context and indicate 'entailment' or 'not_entailment'. +Language: french, acc: 93.20%, prompt: Based on the given context, decide whether the answer to the question is necessarily inferred and mark 'entailment' or 'not_entailment'. +Language: arabic, acc: 93.50%, prompt: As a language expert, evaluate whether the given context calls for an answer and answer 'entailment' or 'not_entailment'. +Language: arabic, acc: 93.50%, prompt: Judge the relationship between the text and the question and answer 'entailment' or 'not_entailment', depending on your language experience. +Language: arabic, acc: 93.50%, prompt: Does the context given indicate the answer to the question? Evaluate and answer 'entailment' or 'not_entailment'. +Language: arabic, acc: 94.00%, prompt: Based on your linguistic knowledge, does the text relate to the question? Answer 'entailment' or 'not_entailment'. +Language: arabic, acc: 93.90%, prompt: As a language expert, determine how the text relates to the question and answer 'entailment' or 'not_entailment'. +Language: arabic, acc: 93.30%, prompt: Does the text support the answer to the question? Answer 'entailment' or 'not_entailment', depending on your language experience. +Language: arabic, acc: 92.90%, prompt: Check the text link to the question and answer 'entailment' or 'not_entailment', depending on your language skills. +Language: arabic, acc: 93.10%, prompt: As a language expert, is there a link between the text and the question? Answer 'entailment' or 'not_entailment'. +Language: arabic, acc: 94.20%, prompt: Based on your language experience, does context help to answer the question? Evaluate and answer 'entailment' or 'not_entailment'. +Language: arabic, acc: 93.50%, prompt: Does the text give a clear answer to the question? Answer 'entailment' or 'not_entailment', depending on your language experience. +Language: spanish, acc: 93.20%, prompt: As a language expert, evaluate whether the given context implies the answer to the question and answer with 'entailment' or 'not_entailment'. +Language: spanish, acc: 93.60%, prompt: Determine whether the information given in the text necessarily implies the veracity of the hypothesis and answer 'entailment' or 'not_entailment'. +Language: spanish, acc: 94.90%, prompt: Analyzes whether the information presented in the paragraph leads to the conclusion of the question and labels the answer as 'entailment' or 'not_entailment'. +Language: spanish, acc: 94.20%, prompt: Indicates whether the information provided in the text is sufficient to conclude the statement and labels the response as 'entailment' or 'not_entailment'. +Language: spanish, acc: 94.10%, prompt: As an expert on the subject, judge whether the information provided in the text justifies the claim and classify the answer as 'entailment' or 'not_entailment'. +Language: spanish, acc: 94.10%, prompt: Evaluates whether the information in the paragraph necessarily supports the conclusion of the hypothesis and responds 'entailment' or 'not_entailment'. +Language: spanish, acc: 93.90%, prompt: Determines whether the information presented in the text logically implies the answer to the question and labels the answer as 'entailment' or 'not_entailment'. +Language: spanish, acc: 94.20%, prompt: Analyzes whether the information provided in the paragraph necessarily leads to the veracity of the hypothesis and classifies the response as 'entailment' or 'not_entailment'. +Language: spanish, acc: 93.70%, prompt: As an expert on the subject, evaluate whether the information presented in the text supports the claim and respond 'entailment' or 'not_entailment'. +Language: spanish, acc: 94.30%, prompt: Indicates whether the information provided in the paragraph necessarily implies the answer to the question and labels the answer as 'entailment' or 'not_entailment'. +Language: japanese, acc: 93.70%, prompt: Rate whether the answer to the question is derived from the given context and answer with 'entailment' or 'not_entailment'. +Language: japanese, acc: 93.20%, prompt: Please answer 'entailment' or 'not_entailment' for the given context and question. +Language: japanese, acc: 93.20%, prompt: Decide whether the answer to the question is derived from the given context and answer 'entailment' or 'not_entailment'. +Language: japanese, acc: 92.60%, prompt: Compare the question with the given context and give the answer 'entailment' or 'not_entailment'. +Language: japanese, acc: 93.90%, prompt: Determinate whether the given context contains the answer to the question and answer with 'entailment' or 'not_entailment'. +Language: japanese, acc: 93.10%, prompt: Estimate the answer of the question from the context and give the answer 'entailment' or 'not_entailment'. +Language: japanese, acc: 93.90%, prompt: Determinate whether the given context is relevant to the question and answer with 'entailment' or 'not_entailment'. +Language: japanese, acc: 93.90%, prompt: Determine whether the given context is relevant to the question and answer with 'entailment' or 'not_entailment'. +Language: japanese, acc: 93.60%, prompt: Determinate whether the given context contains the answer to the question and answer 'entailment' or 'not_entailment'. +Language: japanese, acc: 93.00%, prompt: Answer with 'entailment' or 'not_entailment', inferring from the given context. +Language: korean, acc: 93.40%, prompt: Determine if a given sentence necessarily implies the meaning of another sentence and answer 'entailment' or 'not_entailment'. +Language: korean, acc: 93.50%, prompt: By understanding the relations between sentences, judge whether a given sentence necessarily refers to another sentence and answer with 'entailment' or 'not_entailment'. +Language: korean, acc: 93.80%, prompt: Evaluate whether a given text necessarily indicates the meaning of another text and respond with 'entailment' or 'not_entailment'. +Language: korean, acc: 93.40%, prompt: Understand the relations of a sentence, to determine whether a given sentence necessarily includes other sentences and answer with 'entailment' or 'not_entailment'. +Language: korean, acc: 93.40%, prompt: Judge whether a given content necessarily implies the meaning of another content and answer with 'entailment' or 'not_entailment'. +Language: korean, acc: 93.80%, prompt: Grasp the relations between sentences, determine if a given sentence necessarily contains the meaning of another sentence and respond with 'entailment' or 'not_entailment'. +Language: korean, acc: 93.90%, prompt: Evaluate whether a given text necessarily refers to another text and answer with 'entailment' or 'not_entailment'. +Language: korean, acc: 93.30%, prompt: By comparing the meaning of the sentences, to determine if a given sentence necessarily implies another sentence and answer 'entailment' or 'not_entailment'. +Language: korean, acc: 94.00%, prompt: Evaluate whether the contents given necessarily refer to other contents and answer with 'entailment' or 'not_entailment'. +Language: korean, acc: 83.00%, prompt: By analyzing the relations between sentences, determine if a given sentence does not necessarily include other sentences and answer with 'entailment' or 'not_entailment'. + +# qqp + +## 10 prompts + +Acc: 88.80%, prompt: Determine if the given pair of statements can be considered the same by responding with 'equivalent' or 'not_equivalent'. +Acc: 88.70%, prompt: Examine the following expressions and tell me if they are alike in meaning by using 'equivalent' or 'not_equivalent'. +Acc: 88.50%, prompt: Are the following two questions equivalent or not? Answer me with "equivalent" or "not_equivalent". +Acc: 88.40%, prompt: Analyze if the given set of sentences have the same connotation by answering with 'equivalent' or 'not_equivalent'. +Acc: 88.30%, prompt: Are the meanings of these two phrases the same? Reply with 'equivalent' or 'not_equivalent'. +Acc: 88.20%, prompt: Do these two sentences convey the same meaning? Indicate with 'equivalent' or 'not_equivalent'. +Acc: 88.10%, prompt: Assess whether the following statements are identical in meaning by answering 'equivalent' or 'not_equivalent'. +Acc: 88.10%, prompt: Please indicate if the following pair of sentences share the same meaning by responding with 'equivalent' or 'not_equivalent'. +Acc: 88.10%, prompt: Do the following expressions mean the same thing? Provide your answer as 'equivalent' or 'not_equivalent'. +Acc: 88.00%, prompt: Evaluate whether these two phrases have identical meanings and respond with 'equivalent' or 'not_equivalent'. +Acc: 87.90%, prompt: Can these two statements be considered equal in meaning? Answer with 'equivalent' or 'not_equivalent'. + +Acc: 90.00%, prompt: As a tool for determining question equivalence, review the questions and categorize their similarity as either 'equivalent' or 'not_equivalent'. +Acc: 89.30%, prompt: While performing question comparison analysis, classify the similarity of the following questions as 'equivalent' for equivalent questions or 'not_equivalent' for different questions. +Acc: 89.10%, prompt: Functioning as a question similarity evaluation tool, analyze the given questions and decide if they share the same meaning, responding with 'equivalent' or 'not_equivalent'. +Acc: 88.90%, prompt: As an instrument for question comparison evaluation, consider the questions and determine if their meaning is the same, responding with 'equivalent' for similar questions or 'not_equivalent' for different questions. +Acc: 88.80%, prompt: In your role as a question comparison tool, assess the following pair of questions and classify them as 'equivalent' or 'not_equivalent'. +Acc: 88.70%, prompt: In the capacity of a question assessment system, indicate if the meaning of the provided questions is the same, responding with 'equivalent' or 'not_equivalent'. +Acc: 88.40%, prompt: As a question equivalence detection system, examine the provided questions and respond with 'equivalent' if they are the same in meaning, or 'not_equivalent' if they are different. +Acc: 88.30%, prompt: Working as a question classifier, identify whether the given questions share the same meaning, and respond with 'equivalent' for equivalent questions or 'not_equivalent' for different ones. +Acc: 88.20%, prompt: Acting as a question equivalence instrument, determine if the provided questions are equivalent in meaning, answering with 'equivalent' for similar questions or 'not_equivalent' for dissimilar ones. +Acc: 88.00%, prompt: In the role of a question similarity analyzer, examine the meaning of the provided questions and decide if they are equivalent, answering with 'equivalent' for equivalent questions or 'not_equivalent' for different questions. + +## bertattack + +Original prompt: Determine if the given pair of statements can be considered the same by responding with 'equivalent' or 'not_equivalent'. +Attacked prompt: b"ask if the certain pair of statements can be considered the same by responding with 'equivalent' or 'not_equivalent'. " +Original acc: 88.80%, attacked acc: 88.00%, dropped acc: 0.80% + +Original prompt: Examine the following expressions and tell me if they are alike in meaning by using 'equivalent' or 'not_equivalent'. +Attacked prompt: b"Examine the past expressions and give me if they are common in meaning by putting 'equivalent' or 'not_equivalent'. " +Original acc: 88.70%, attacked acc: 82.90%, dropped acc: 5.80% + +Original prompt: Are the following two questions equivalent or not? Answer me with "equivalent" or "not_equivalent". +Attacked prompt: b'were the following twice equations equivalent or not? Answer me with "equivalent" or "not_equivalent". ' +Original acc: 88.50%, attacked acc: 87.30%, dropped acc: 1.20% + +Original prompt: As a tool for determining question equivalence, review the questions and categorize their similarity as either 'equivalent' or 'not_equivalent'. +Attacked prompt: b"according a tool for identifying concept equivalence, do the questions and tcsconsider their compared as neither 'equivalent' or 'not_equivalent'. " +Original acc: 90.10%, attacked acc: 74.30%, dropped acc: 15.80% + +Original prompt: While performing question comparison analysis, classify the similarity of the following questions as 'equivalent' for equivalent questions or 'not_equivalent' for different questions. +Attacked prompt: b"While performing question comparison analysis, assign the difference of the following expressions as 'equivalent' for equivalent questions or 'not_equivalent' for combined measures. " +Original acc: 89.30%, attacked acc: 86.00%, dropped acc: 3.30% + +Original prompt: Functioning as a question similarity evaluation tool, analyze the given questions and decide if they share the same meaning, responding with 'equivalent' or 'not_equivalent'. +Attacked prompt: b"Functioning as a question change evaluation tool, test the presented yes and tell if they share the same meaning, responding with 'equivalent' or 'not_equivalent'. " +Original acc: 89.10%, attacked acc: 87.10%, dropped acc: 2.00% + +## checklist + +Original prompt: Determine if the given pair of statements can be considered the same by responding with 'equivalent' or 'not_equivalent'. +Attacked prompt: b"Determine if the given pair of statements can be considered the same by responding with 'equivalent' or 'not_equivalent' AMsRIKZniY. " +Original acc: 88.80%, attacked acc: 88.90%, dropped acc: -0.10% + +Original prompt: Examine the following expressions and tell me if they are alike in meaning by using 'equivalent' or 'not_equivalent'. +Attacked prompt: b"Examine the following expressions and tell me if they are alike in meaning by using 'equivalent' or 'not_equivalent' LkF0FZxMZ4. " +Original acc: 88.70%, attacked acc: 88.60%, dropped acc: 0.10% + +Original prompt: Are the following two questions equivalent or not? Answer me with "equivalent" or "not_equivalent". +Attacked prompt: b'Are the following two questions equivalent or not? Answer me with "equivalent" or "not_equivalent Cev0s49fbe". ' +Original acc: 88.50%, attacked acc: 88.40%, dropped acc: 0.10% + +Original prompt: As a tool for determining question equivalence, review the questions and categorize their similarity as either 'equivalent' or 'not_equivalent'. +Attacked prompt: b"As a tool for determining question equivalence, review the questions and categorize their similarity as either 'equivalent' or 'not_equivalent' 6a4Yn3RGVc. " +Original acc: 90.00%, attacked acc: 89.70%, dropped acc: 0.30% + +Original prompt: While performing question comparison analysis, classify the similarity of the following questions as 'equivalent' for equivalent questions or 'not_equivalent' for different questions. +Attacked prompt: b"While performing question comparison analysis, classify the similarity of the following questions as 'equivalent' for equivalent questions or 'not_equivalent' for different questions ofOQXLxiW4. " +Original acc: 89.30%, attacked acc: 89.20%, dropped acc: 0.10% + +Original prompt: Functioning as a question similarity evaluation tool, analyze the given questions and decide if they share the same meaning, responding with 'equivalent' or 'not_equivalent'. +Attacked prompt: b"Functioning as a question similarity evaluation tool, analyze the given questions and decide if they share the same meaning, responding with 'equivalent' or 'not_equivalent' KjPJJ2a7RB. " +Original acc: 89.10%, attacked acc: 88.70%, dropped acc: 0.40% + +## deepwordbug + +Original prompt: Determine if the given pair of statements can be considered the same by responding with 'equivalent' or 'not_equivalent'. +Attacked prompt: b"DeterminIe if the gievn pair of statements can be considered the same by responding with 'equivalent' or 'not_equivalent'. " +Original acc: 88.80%, attacked acc: 88.40%, dropped acc: 0.40% + +Original prompt: Examine the following expressions and tell me if they are alike in meaning by using 'equivalent' or 'not_equivalent'. +Attacked prompt: b"Examine the following expressiZns and tell me if they are aike in meaning by wusing 'equivalent' or 'not_equivalent'. " +Original acc: 88.70%, attacked acc: 87.40%, dropped acc: 1.30% + +Original prompt: Are the following two questions equivalent or not? Answer me with "equivalent" or "not_equivalent". +Attacked prompt: b'Are the following two questions equivalent or not? Answer me with "equivalent" or "not_equivalent". ' +Original acc: 88.50%, attacked acc: 88.50%, dropped acc: 0.20% + +Original prompt: As a tool for determining question equivalence, review the questions and categorize their similarity as either 'equivalent' or 'not_equivalent'. +Attacked prompt: b"As a tool for determining question equivalence, rPeview the questions and categocrize their simiXlarity as either 'equivalent' or 'not_equivalent'. " +Original acc: 90.00%, attacked acc: 88.00%, dropped acc: 2.00% + +Original prompt: While performing question comparison analysis, classify the similarity of the following questions as 'equivalent' for equivalent questions or 'not_equivalent' for different questions. +Attacked prompt: b"While performing Pquestion comparison analysig, classify the simioarity of the following queFtions as 'equivalent' for equivalent questions or 'not_equivalent' for different questions. " +Original acc: 89.30%, attacked acc: 87.60%, dropped acc: 1.70% + +Original prompt: Functioning as a question similarity evaluation tool, analyze the given questions and decide if they share the same meaning, responding with 'equivalent' or 'not_equivalent'. +Attacked prompt: b"Functioning as a queFstion imilarity evaluation too, analJyze the given questions and deicde if they hsare the same meaning, respnoding with 'equivalent' or 'not_equivalent'. " +Original acc: 89.10%, attacked acc: 87.70%, dropped acc: 1.40% + +## stresstest + +Original prompt: Determine if the given pair of statements can be considered the same by responding with 'equivalent' or 'not_equivalent'. +Attacked prompt: b"Determine if the given pair of statements can be considered the same by responding with 'equivalent' or 'not_equivalent' and false is not true . " +Original acc: 88.80%, attacked acc: 88.80%, dropped acc: 0.00% + +Original prompt: Examine the following expressions and tell me if they are alike in meaning by using 'equivalent' or 'not_equivalent'. +Attacked prompt: b"Examine the following expressions and tell me if they are alike in meaning by using 'equivalent' or 'not_equivalent' and false is not true . " +Original acc: 88.70%, attacked acc: 88.40%, dropped acc: 0.30% + +Original prompt: Are the following two questions equivalent or not? Answer me with "equivalent" or "not_equivalent". +Attacked prompt: b'Are the following two questions equivalent or not? Answer me with "equivalent" or "not_equivalent and true is true ". ' +Original acc: 88.50%, attacked acc: 88.00%, dropped acc: 0.50% + +Original prompt: As a tool for determining question equivalence, review the questions and categorize their similarity as either 'equivalent' or 'not_equivalent'. +Attacked prompt: b"As a tool for determining question equivalence, review the questions and categorize their similarity as either 'equivalent' or 'not_equivalent' and true is true and true is true and true is true and true is true and true is true . " +Original acc: 90.00%, attacked acc: 89.50%, dropped acc: 0.50% + +Original prompt: While performing question comparison analysis, classify the similarity of the following questions as 'equivalent' for equivalent questions or 'not_equivalent' for different questions. +Attacked prompt: b"While performing question comparison analysis, classify the similarity of the following questions as 'equivalent' for equivalent questions or 'not_equivalent' for different questions and true is true and true is true and true is true and true is true and true is true . " +Original acc: 89.30%, attacked acc: 89.30%, dropped acc: 0.00% + +Original prompt: Functioning as a question similarity evaluation tool, analyze the given questions and decide if they share the same meaning, responding with 'equivalent' or 'not_equivalent'. +Attacked prompt: b"Functioning as a question similarity evaluation tool, analyze the given questions and decide if they share the same meaning, responding with 'equivalent' or 'not_equivalent' and false is not true . " +Original acc: 89.10%, attacked acc: 88.90%, dropped acc: 0.20% + +## textbugger + +Original prompt: Determine if the given pair of statements can be considered the same by responding with 'equivalent' or 'not_equivalent'. +Attacked prompt: b"Defining if the given paired of statements can be considered the same by responds with 'equivalent' or 'not_equivalent'. " +Original acc: 88.80%, attacked acc: 87.60%, dropped acc: 1.20% + +Original prompt: Examine the following expressions and tell me if they are alike in meaning by using 'equivalent' or 'not_equivalent'. +Attacked prompt: b"Examine the following expressions and tell me if they are ali ke in meaning by using 'equivalent' or 'not_equivalent'. " +Original acc: 88.70%, attacked acc: 87.60%, dropped acc: 1.10% + +Original prompt: Are the following two questions equivalent or not? Answer me with "equivalent" or "not_equivalent". +Attacked prompt: b'Are the following two questions equivalent or not? Answer me with "equivalent" or "not_equivalent". ' +Original acc: 88.40%, attacked acc: 88.40%, dropped acc: 0.30% + +Original prompt: As a tool for determining question equivalence, review the questions and categorize their similarity as either 'equivalent' or 'not_equivalent'. +Attacked prompt: b"As a tool for deciding que\xd1\x95tion equivalence, review the questions and classifications their portrait as neither 'equivalent' or 'not_equivalent'. " +Original acc: 90.00%, attacked acc: 87.60%, dropped acc: 2.40% + +Original prompt: While performing question comparison analysis, classify the similarity of the following questions as 'equivalent' for equivalent questions or 'not_equivalent' for different questions. +Attacked prompt: b"Whilst performing question comparison analyses, classify the likeness of the following questions as 'equivalent' for equivalent questions or 'not_equivalent' for different questions. " +Original acc: 89.30%, attacked acc: 88.30%, dropped acc: 1.00% + +Original prompt: Functioning as a question similarity evaluation tool, analyze the given questions and decide if they share the same meaning, responding with 'equivalent' or 'not_equivalent'. +Attacked prompt: b"Functioning as a question portrait evaluation tool, aanlyze the given questio\xd5\xb8s and deci de if they share the same meaning, responding with 'equivalent' or 'not_equivalent'. " +Original acc: 89.10%, attacked acc: 88.10%, dropped acc: 1.00% + +## textfooler + +Original prompt: Determine if the given pair of statements can be considered the same by responding with 'equivalent' or 'not_equivalent'. +Attacked prompt: b"Defined if the given pair of statements can is considered the same by responded with 'equivalent' or 'not_equivalent'. " +Original acc: 88.80%, attacked acc: 87.70%, dropped acc: 1.10% + +Original prompt: Examine the following expressions and tell me if they are alike in meaning by using 'equivalent' or 'not_equivalent'. +Attacked prompt: b"Examine the afterward words and saying me if they are uniformly in connotation by using 'equivalent' or 'not_equivalent'. " +Original acc: 88.70%, attacked acc: 85.90%, dropped acc: 2.80% + +Original prompt: Are the following two questions equivalent or not? Answer me with "equivalent" or "not_equivalent". +Attacked prompt: b'Exists the farther two facets equivalent or not? Answer me with "equivalent" or "not_equivalent". ' +Original acc: 88.40%, attacked acc: 87.20%, dropped acc: 1.20% + +Original prompt: As a tool for determining question equivalence, review the questions and categorize their similarity as either 'equivalent' or 'not_equivalent'. +Attacked prompt: b"Because a tool for determining question equivalence, examination the queries and classifications their likeness as either 'equivalent' or 'not_equivalent'. " +Original acc: 90.00%, attacked acc: 87.60%, dropped acc: 2.40% + +Original prompt: While performing question comparison analysis, classify the similarity of the following questions as 'equivalent' for equivalent questions or 'not_equivalent' for different questions. +Attacked prompt: b"While performing question comparing analysis, classifications the likeness of the following queries as 'equivalent' for equivalent question or 'not_equivalent' for diverse item. " +Original acc: 89.30%, attacked acc: 87.60%, dropped acc: 1.70% + +Original prompt: Functioning as a question similarity evaluation tool, analyze the given questions and decide if they share the same meaning, responding with 'equivalent' or 'not_equivalent'. +Attacked prompt: b"Functional as a question resemblance evaluation mechanism, analytical the given questions and chose if they exchange the same meaning, responding with 'equivalent' or 'not_equivalent'. " +Original acc: 89.10%, attacked acc: 87.60%, dropped acc: 1.50% + +## translation + +Language: chinese, acc: 89.70%, prompt: As a tool for determining the equivalence of problems, the problems are examined and their similarity is classified as 'equivalent' or 'not_equivalent'. +Language: chinese, acc: 89.30%, prompt: Please compare the similarity of two sentences and put them into the category of 'equivalent' or 'not_equivalent'. +Language: chinese, acc: 88.90%, prompt: Two sentences are classified as 'equivalent' or 'not_equivalent' for their similarity. +Language: chinese, acc: 89.90%, prompt: You can determine how similar the questions are by comparing them and categorizing them as 'equivalent' or 'not_equivalent'. +Language: chinese, acc: 89.50%, prompt: Using the method of contrast, the similarity of these problems is divided into two categories: 'equivalent' or 'not_equivalent'. +Language: chinese, acc: 88.40%, prompt: By comparing these issues, you can classify them as 'equivalent' or 'not_equivalent'. +Language: chinese, acc: 89.50%, prompt: To determine whether the questions are similar, put them into the category of 'equivalent' or 'not_equivalent'. +Language: chinese, acc: 89.60%, prompt: Divide the similarity of these questions into 'equivalent' or 'not_equivalent' categories. +Language: chinese, acc: 90.10%, prompt: Using the similarity assessment tool, these questions were classified as 'equivalent' or 'not_equivalent'. +Language: chinese, acc: 89.60%, prompt: By analyzing the similarity of these problems, they are divided into categories of 'equivalent' or 'not_equivalent'. +Language: french, acc: 89.50%, prompt: As a tool to determine the equivalence of questions, review the questions and rank their similarity as 'equivalent' or 'not_equivalent'. +Language: french, acc: 89.30%, prompt: Please compare the similarity of two sentences and classify them as 'equivalent' or 'not_equivalent'. +Language: french, acc: 90.00%, prompt: Based on the similarity of two sentences, classify them as 'equivalent' or 'not_equivalent'. +Language: french, acc: 90.10%, prompt: You can determine the similarity between these questions by comparing them and classifying them as 'equivalent' or 'not_equivalent'. +Language: french, acc: 89.90%, prompt: Use a comparative method to divide the similarity of these questions into two categories: 'equivalent' or 'not_equivalent'. +Language: french, acc: 88.10%, prompt: By comparing these questions, you can classify them as 'equivalent' or 'not_equivalent'. +Language: french, acc: 89.70%, prompt: Determine whether these questions are similar or not, and then classify them as 'equivalent' or 'not_equivalent'. +Language: french, acc: 89.80%, prompt: Divide the similarity of these questions into two categories: 'equivalent' or 'not_equivalent'. +Language: french, acc: 90.10%, prompt: Use a similarity assessment tool to classify these questions as 'equivalent' or 'not_equivalent'. +Language: french, acc: 89.70%, prompt: By analyzing the similarity of these questions, you can divide them into two categories: 'equivalent' or 'not_equivalent'. +Language: arabic, acc: 89.30%, prompt: As a tool for determining an equation of questions, review the questions and classify their similarity as either 'equivalent' or 'not_equivalent'. +Language: arabic, acc: 89.80%, prompt: When using questions in the classification domain, please classify the similarity between the questions as 'equivalent' or 'not_equivalent'. +Language: arabic, acc: 89.10%, prompt: To determine an equation of questions, you must review the questions and classify their similarity as 'equivalent' or 'not_equivalent'. +Language: arabic, acc: 88.80%, prompt: Questions can be classified as 'equivalent' or 'not_equivalent' when used to identify classifications. +Language: arabic, acc: 89.10%, prompt: Classification of question similarity as 'equivalent' or 'not_equivalent' is used as a tool to determine the classification of questions. +Language: arabic, acc: 89.00%, prompt: Classify the similarity of the questions as 'equivalent' or 'not_equivalent' to determine the equation of the questions. +Language: arabic, acc: 89.30%, prompt: Identifying the similarity of questions and classifying them as 'equivalent' or 'not_equivalent' is an important tool in determining the classification of questions. +Language: arabic, acc: 89.00%, prompt: When classifying questions, their similarity can be classified as 'equivalent' or 'not_equivalent' to determine the correct classification. +Language: arabic, acc: 89.50%, prompt: The similarity of questions should be classified as 'equivalent' or 'not_equivalent' when used to determine the equation of questions. +Language: arabic, acc: 89.10%, prompt: Identifying the similarity of questions and classifying them as 'equivalent' or 'not_equivalent' helps to correctly classify questions. +Language: spanish, acc: 90.00%, prompt: As a tool to determine the equivalence of questions, it reviews the questions and classifies their similarity as 'equivalent' or 'not_equivalent'. +Language: spanish, acc: 89.30%, prompt: Evaluate the similarity between questions and classify them as 'equivalent' or 'not_equivalent' to determine their equivalence. +Language: spanish, acc: 89.70%, prompt: Determine whether two questions are 'equivalent' or 'not_equivalent' based on similarity and characteristics. +Language: spanish, acc: 89.10%, prompt: Classifies the similarity between questions as 'equivalent' or 'not_equivalent' to determine their equivalence. +Language: spanish, acc: 89.60%, prompt: Review the questions and rate them as 'equivalent' or 'not_equivalent' based on their similarity and content. +Language: spanish, acc: 89.20%, prompt: As part of the classification task of questions, it determines their equivalence by categorizing their similarity as 'equivalent' or 'not_equivalent'. +Language: spanish, acc: 89.50%, prompt: Analyze the similarity between questions and classify them as 'equivalent' or 'not_equivalent' to determine their equivalence. +Language: spanish, acc: 90.10%, prompt: As a method of identifying the equivalence of questions, it categorizes their similarity as 'equivalent' or 'not_equivalent'. +Language: spanish, acc: 89.30%, prompt: To determine the equivalence between questions, check their similarity and classify them as 'equivalent' or 'not_equivalent'. +Language: spanish, acc: 89.90%, prompt: Classify the similarity between questions as 'equivalent' or 'not_equivalent' to determine whether they are equivalent or not. +Language: japanese, acc: 89.40%, prompt: As a tool to determine the equivalence of the question, review the question and categorize its similarities into 'equivalent' or 'not_equivalent' categories. +Language: japanese, acc: 88.60%, prompt: Work on text sorting tasks labeled 'equivalent' or 'not_equivalent'. +Language: japanese, acc: 88.60%, prompt: For text classification tasks, use the labels 'equivalent' or 'not_equivalent' to determine the equivalence of statements. +Language: japanese, acc: 88.50%, prompt: In the MRPC dataset, use the labels 'equivalent' or 'not_equivalent' to classify the equivalence of statements. +Language: japanese, acc: 88.80%, prompt: As a tool for determining equivalence, check sentences and categorize them into 'equivalent' or 'not_equivalent' categories. +Language: japanese, acc: 88.40%, prompt: Use the labels 'equivalent' or 'not_equivalent' to determine the equivalence of statements in text classification tasks. +Language: japanese, acc: 88.90%, prompt: In the text classification task of the MRPC data set, classify the equivalence of statements with labels of 'equivalent' or 'not_equivalent'. +Language: japanese, acc: 89.00%, prompt: As a tool to determine the equivalence of statements, categorize statements into 'equivalent' or 'not_equivalent' categories. +Language: japanese, acc: 88.50%, prompt: In a text classification task, classify the equivalence of statements using labels of 'equivalent' or 'not_equivalent'. +Language: japanese, acc: 88.80%, prompt: Do a text classification task to determine the equivalence of statements, labeled 'equivalent' or 'not_equivalent'. +Language: korean, acc: 88.30%, prompt: Classify two given sentences as 'equivalent' or 'not_equivalent' by discriminating whether they have the same meaning. +Language: korean, acc: 89.80%, prompt: Determine sentence equivalence by judging the similarity of two sentences with 'equivalent' or 'not_equivalent'. +Language: korean, acc: 88.70%, prompt: Classify the similarity of sentences as 'equivalent' or 'not_equivalent' by judging whether two sentences have the same meaning. +Language: korean, acc: 89.30%, prompt: Determine if two given sentences are equivalent to each other, and classify their similarity as 'equivalent' or 'not_equivalent'. +Language: korean, acc: 89.20%, prompt: Compare two given sentences to determine sentence equivalence, and classify their similarities as 'equivalent' or 'not_equivalent'. +Language: korean, acc: 87.70%, prompt: Classify sentence equivalence as 'equivalent' or 'not_equivalent' by judging whether two sentences have the same meaning to each other. +Language: korean, acc: 89.30%, prompt: Determine if two sentences have the same meaning, and classify their similarities as 'equivalent' or 'not_equivalent'. +Language: korean, acc: 89.10%, prompt: Compare two given sentences to determine their equivalence, and classify their similarities as 'equivalent' or 'not_equivalent'. +Language: korean, acc: 89.30%, prompt: Review two sentences to evaluate sentence equivalence, and classify their similarities as 'equivalent' or 'not_equivalent'. +Language: korean, acc: 87.80%, prompt: Judge whether two sentences have the same meaning to each other, and determine the sentence equivalence with 'equivalent' or 'not_equivalent'. + +# rte + +## 10 prompts + +Acc: 93.50%, prompt: Does the relationship between the given sentences represent entailment or not_entailment? Respond with 'entailment' or 'not_entailment'. +Acc: 93.50%, prompt: Identify whether the given pair of sentences demonstrates entailment or not_entailment. Answer with 'entailment' or 'not_entailment'. +Acc: 93.50%, prompt: Determine if the given pair of sentences displays entailment or not_entailment. Respond with 'entailment' or 'not_entailment'. +Acc: 93.14%, prompt: Examine the pair of sentences and determine if they exhibit entailment or not_entailment. Answer with either 'entailment' or 'not_entailment'. +Acc: 93.14%, prompt: Review the two statements and categorize their relationship as either 'entailment' or 'not_entailment'. +Acc: 92.78%, prompt: Are the following two sentences entailment or not_entailment? Answer me with "entailment" or "not_entailment", just one word. +Acc: 92.78%, prompt: Assess the connection between the following sentences and classify it as 'entailment' or 'not_entailment'. +Acc: 92.78%, prompt: Analyze the two provided sentences and decide if their relationship is 'entailment' or 'not_entailment'. +Acc: 92.78%, prompt: Please classify the relationship between the provided sentences as 'entailment' or 'not_entailment'. +Acc: 92.78%, prompt: Considering the two sentences, identify if their relationship is 'entailment' or 'not_entailment'. +Acc: 92.42%, prompt: Indicate if the connection between the following sentences is 'entailment' or 'not_entailment'. + +Acc: 93.86%, prompt: Working as an entailment classifier, identify whether the given pair of sentences displays entailment or not_entailment. Respond with 'entailment' or 'not_entailment'. +Acc: 93.50%, prompt: Acting as an entailment detection instrument, determine if the given pair of sentences demonstrates entailment or not_entailment. Answer with 'entailment' or 'not_entailment'. +Acc: 93.50%, prompt: As a tool for determining entailment relationships, review the two statements and categorize their connection as either 'entailment' or 'not_entailment'. +Acc: 93.50%, prompt: As an instrument for entailment evaluation, consider the two sentences and determine if their relationship is 'entailment' or 'not_entailment'. Respond with 'entailment' or 'not_entailment'. +Acc: 93.14%, prompt: In your role as an entailment analysis tool, assess the relationship between the given sentences and classify it as 'entailment' or 'not_entailment'. +Acc: 93.14%, prompt: Functioning as an entailment evaluation tool, analyze the provided sentences and decide if their relationship is 'entailment' or 'not_entailment'. +Acc: 93.14%, prompt: While performing entailment analysis, classify the relationship between the provided sentences as 'entailment' or 'not_entailment'. +Acc: 93.14%, prompt: In the role of a semantic relationship analyzer, examine the connection between the given sentences and decide if they exhibit entailment or not_entailment. Answer with 'entailment' or 'not_entailment'. +Acc: 92.78%, prompt: As an entailment identification system, examine the connection between the following sentences and respond with 'entailment' or 'not_entailment'. +Acc: 92.78%, prompt: In the capacity of an entailment assessment system, indicate if the link between the following sentences is 'entailment' or 'not_entailment'. + +## bertattack + +Original prompt: Does the relationship between the given sentences represent entailment or not_entailment? Respond with 'entailment' or 'not_entailment'. +Attacked prompt: b"a the relationship between the given sentences carry entailment or not_entailment? Respond with 'entailment' or 'not_entailment'. " +Original acc: 93.50%, attacked acc: 92.78%, dropped acc: 0.72% + +Original prompt: Identify whether the given pair of sentences demonstrates entailment or not_entailment. Answer with 'entailment' or 'not_entailment'. +Attacked prompt: b"a as the given pair of verb demonstrates entailment or not_entailment. question with 'entailment' or 'not_entailment'. " +Original acc: 93.50%, attacked acc: 91.34%, dropped acc: 2.17% + +Original prompt: Determine if the given pair of sentences displays entailment or not_entailment. Respond with 'entailment' or 'not_entailment'. +Attacked prompt: b"be if the given conjunction of and displays entailment or not_entailment. Respond with 'entailment' or 'not_entailment'. " +Original acc: 93.50%, attacked acc: 92.06%, dropped acc: 1.44% + +Original prompt: Working as an entailment classifier, identify whether the given pair of sentences displays entailment or not_entailment. Respond with 'entailment' or 'not_entailment'. +Attacked prompt: b"acting as an entailment classindicator, identify neither the given pair of sentences displays entailment or not_entailment. reply with 'entailment' or 'not_entailment'. " +Original acc: 93.86%, attacked acc: 65.34%, dropped acc: 28.52% + +Original prompt: Acting as an entailment detection instrument, determine if the given pair of sentences demonstrates entailment or not_entailment. Answer with 'entailment' or 'not_entailment'. +Attacked prompt: b"Acting as an entailment detection instrument, determine if the given complement of verbs provides entailment or not_entailment. sentence with 'entailment' or 'not_entailment'. " +Original acc: 93.50%, attacked acc: 89.53%, dropped acc: 3.97% + +Original prompt: As a tool for determining entailment relationships, review the two statements and categorize their connection as either 'entailment' or 'not_entailment'. +Attacked prompt: b"her a tool for determining entailment about, structure the two statements and categorize their connection as either 'entailment' or 'not_entailment'. " +Original acc: 93.50%, attacked acc: 91.70%, dropped acc: 1.81% + +## checklist + +Original prompt: Does the relationship between the given sentences represent entailment or not_entailment? Respond with 'entailment' or 'not_entailment'. +Attacked prompt: b"Does the relationship between the given sentences represent entailment or not_entailment? Respond with 'entailment' or 'not_entailment' CuVpbbkC4c. " +Original acc: 93.50%, attacked acc: 93.14%, dropped acc: 0.36% + +Original prompt: Identify whether the given pair of sentences demonstrates entailment or not_entailment. Answer with 'entailment' or 'not_entailment'. +Attacked prompt: b"Identify whether the given pair of sentences demonstrates entailment or not_entailment. Answer with 'entailment' or 'not_entailment' d6ZQ3u0GBQ. " +Original acc: 93.50%, attacked acc: 92.78%, dropped acc: 0.72% + +Original prompt: Determine if the given pair of sentences displays entailment or not_entailment. Respond with 'entailment' or 'not_entailment'. +Attacked prompt: b"Determine if the given pair of sentences displays entailment or not_entailment. Respond with 'entailment' or 'not_entailment' 5yWbBXztUY. " +Original acc: 93.50%, attacked acc: 93.14%, dropped acc: 0.36% + +Original prompt: Working as an entailment classifier, identify whether the given pair of sentences displays entailment or not_entailment. Respond with 'entailment' or 'not_entailment'. +Attacked prompt: b"Working as an entailment classifier, identify whether the given pair of sentences displays entailment or not_entailment. Respond with 'entailment' or 'not_entailment' CuVpbbkC4c. " +Original acc: 93.86%, attacked acc: 93.50%, dropped acc: 0.36% + +Original prompt: Acting as an entailment detection instrument, determine if the given pair of sentences demonstrates entailment or not_entailment. Answer with 'entailment' or 'not_entailment'. +Attacked prompt: b"Acting as an entailment detection instrument, determine if the given pair of sentences demonstrates entailment or not_entailment. Answer with 'entailment' or 'not_entailment' BWmsLx8xOA. " +Original acc: 93.50%, attacked acc: 93.14%, dropped acc: 0.36% + +Original prompt: As a tool for determining entailment relationships, review the two statements and categorize their connection as either 'entailment' or 'not_entailment'. +Attacked prompt: b"As a tool for determining entailment relationships, review the two statements and categorize their connection as either 'entailment' or 'not_entailment' 5XeflW1ZJc. " +Original acc: 93.50%, attacked acc: 93.14%, dropped acc: 0.36% + +## deepwordbug + +Original prompt: Does the relationship between the given sentences represent entailment or not_entailment? Respond with 'entailment' or 'not_entailment'. +Attacked prompt: b"Yoes the relationship between the given sentences repersent entailment or not_entailment? Respond with 'entailment' or 'not_entailment'. " +Original acc: 93.50%, attacked acc: 93.14%, dropped acc: 0.36% + +Original prompt: Identify whether the given pair of sentences demonstrates entailment or not_entailment. Answer with 'entailment' or 'not_entailment'. +Attacked prompt: b"Identify whDther the given pair of sentences demonstrates entailment or not_entailment. Answer with 'entailment' or 'not_entailment'. " +Original acc: 93.50%, attacked acc: 93.14%, dropped acc: 0.36% + +Original prompt: Determine if the given pair of sentences displays entailment or not_entailment. Respond with 'entailment' or 'not_entailment'. +Attacked prompt: b"Determine if the given paGr of sentenecs displays entailment or not_entailment. Respond with 'entailment' or 'not_entailment'. " +Original acc: 93.50%, attacked acc: 92.42%, dropped acc: 1.08% + +Original prompt: Working as an entailment classifier, identify whether the given pair of sentences displays entailment or not_entailment. Respond with 'entailment' or 'not_entailment'. +Attacked prompt: b"Woeking as an entailment classifier, identify whether the given pair of sentences diplays entailment or not_entailment. Respond with 'entailment' or 'not_entailment'. " +Original acc: 93.86%, attacked acc: 92.78%, dropped acc: 1.08% + +Original prompt: Acting as an entailment detection instrument, determine if the given pair of sentences demonstrates entailment or not_entailment. Answer with 'entailment' or 'not_entailment'. +Attacked prompt: b"Acting as an entailment detection instrument, determine if the given pair of sentences demonstrates entailment or not_entailment. Answer with 'entailment' or 'not_entailment'. " +Original acc: 93.50%, attacked acc: 93.50%, dropped acc: 0.36% + +Original prompt: As a tool for determining entailment relationships, review the two statements and categorize their connection as either 'entailment' or 'not_entailment'. +Attacked prompt: b"AL a tool for determining entailment relationhsips, review the two staJements and categorize their connection as either 'entailment' or 'not_entailment'. " +Original acc: 93.50%, attacked acc: 92.42%, dropped acc: 1.08% + +## stresstest + +Original prompt: Does the relationship between the given sentences represent entailment or not_entailment? Respond with 'entailment' or 'not_entailment'. +Attacked prompt: b"Does the relationship between the given sentences represent entailment or not_entailment? Respond with 'entailment' or 'not_entailment' and true is true and true is true and true is true and true is true and true is true . " +Original acc: 93.50%, attacked acc: 92.78%, dropped acc: 0.72% + +Original prompt: Identify whether the given pair of sentences demonstrates entailment or not_entailment. Answer with 'entailment' or 'not_entailment'. +Attacked prompt: b"Identify whether the given pair of sentences demonstrates entailment or not_entailment. Answer with 'entailment' or 'not_entailment' and true is true and true is true and true is true and true is true and true is true . " +Original acc: 93.50%, attacked acc: 93.14%, dropped acc: 0.36% + +Original prompt: Determine if the given pair of sentences displays entailment or not_entailment. Respond with 'entailment' or 'not_entailment'. +Attacked prompt: b"Determine if the given pair of sentences displays entailment or not_entailment. Respond with 'entailment' or 'not_entailment' and true is true and true is true and true is true and true is true and true is true . " +Original acc: 93.50%, attacked acc: 93.14%, dropped acc: 0.36% + +Original prompt: Working as an entailment classifier, identify whether the given pair of sentences displays entailment or not_entailment. Respond with 'entailment' or 'not_entailment'. +Attacked prompt: b"Working as an entailment classifier, identify whether the given pair of sentences displays entailment or not_entailment. Respond with 'entailment' or 'not_entailment' and true is true and true is true and true is true and true is true and true is true . " +Original acc: 93.86%, attacked acc: 92.78%, dropped acc: 1.08% + +Original prompt: Acting as an entailment detection instrument, determine if the given pair of sentences demonstrates entailment or not_entailment. Answer with 'entailment' or 'not_entailment'. +Attacked prompt: b"Acting as an entailment detection instrument, determine if the given pair of sentences demonstrates entailment or not_entailment. Answer with 'entailment' or 'not_entailment' and true is true and true is true and true is true and true is true and true is true . " +Original acc: 93.50%, attacked acc: 93.14%, dropped acc: 0.36% + +Original prompt: As a tool for determining entailment relationships, review the two statements and categorize their connection as either 'entailment' or 'not_entailment'. +Attacked prompt: b"As a tool for determining entailment relationships, review the two statements and categorize their connection as either 'entailment' or 'not_entailment' and true is true and true is true and true is true and true is true and true is true . " +Original acc: 93.50%, attacked acc: 92.06%, dropped acc: 1.44% + +## textbugger + +Original prompt: Does the relationship between the given sentences represent entailment or not_entailment? Respond with 'entailment' or 'not_entailment'. +Attacked prompt: b"Does the relationship between the afforded sentences re present entailment or not_entailment? Respond with 'entailment' or 'not_entailment'. " +Original acc: 93.50%, attacked acc: 92.78%, dropped acc: 0.72% + +Original prompt: Identify whether the given pair of sentences demonstrates entailment or not_entailment. Answer with 'entailment' or 'not_entailment'. +Attacked prompt: b"Identifying whether the given pair of sentencing demonstrates entailment or not_entailment. Respond with 'entailment' or 'not_entailment'. " +Original acc: 93.50%, attacked acc: 92.42%, dropped acc: 1.08% + +Original prompt: Determine if the given pair of sentences displays entailment or not_entailment. Respond with 'entailment' or 'not_entailment'. +Attacked prompt: b"Determine if the given pair of penalties displays entailment or not_entailment. Respond with 'entailment' or 'not_entailment'. " +Original acc: 93.50%, attacked acc: 92.78%, dropped acc: 0.72% + +Original prompt: Working as an entailment classifier, identify whether the given pair of sentences displays entailment or not_entailment. Respond with 'entailment' or 'not_entailment'. +Attacked prompt: b"Working as an entailment classifier, identify both the given piar of sentences displaying entailment or not_entailment. Respond with 'entailment' or 'not_entailment'. " +Original acc: 93.86%, attacked acc: 90.97%, dropped acc: 2.89% + +Original prompt: Acting as an entailment detection instrument, determine if the given pair of sentences demonstrates entailment or not_entailment. Answer with 'entailment' or 'not_entailment'. +Attacked prompt: b"Acting as an entailment detection instrument, determine if the given pair of senetnces demonstrates entailment or not_entailment. Answe\xe2\xb2\x85 with 'entailment' or 'not_entailment'. " +Original acc: 93.50%, attacked acc: 92.42%, dropped acc: 1.08% + +Original prompt: As a tool for determining entailment relationships, review the two statements and categorize their connection as either 'entailment' or 'not_entailment'. +Attacked prompt: b"As a tool for deermining entailment relationships, review the secondly statements and categor\xd1\x96ze their connection as either 'entailment' or 'not_entailment'. " +Original acc: 93.50%, attacked acc: 92.06%, dropped acc: 1.44% + +## textfooler + +Original prompt: Does the relationship between the given sentences represent entailment or not_entailment? Respond with 'entailment' or 'not_entailment'. +Attacked prompt: b"Does the relationship between the given sentences depicted entailment or not_entailment? Respond with 'entailment' or 'not_entailment'. " +Original acc: 93.50%, attacked acc: 92.78%, dropped acc: 0.72% + +Original prompt: Identify whether the given pair of sentences demonstrates entailment or not_entailment. Answer with 'entailment' or 'not_entailment'. +Attacked prompt: b"Deciding whether the given pair of sentencing demonstrates entailment or not_entailment. Answer with 'entailment' or 'not_entailment'. " +Original acc: 93.50%, attacked acc: 92.42%, dropped acc: 1.08% + +Original prompt: Determine if the given pair of sentences displays entailment or not_entailment. Respond with 'entailment' or 'not_entailment'. +Attacked prompt: b"Define if the given pair of chastisement displays entailment or not_entailment. Answered with 'entailment' or 'not_entailment'. " +Original acc: 93.50%, attacked acc: 92.42%, dropped acc: 1.08% + +Original prompt: Working as an entailment classifier, identify whether the given pair of sentences displays entailment or not_entailment. Respond with 'entailment' or 'not_entailment'. +Attacked prompt: b"Working as an entailment classifier, identify whether the given torque of sanction displays entailment or not_entailment. Respond with 'entailment' or 'not_entailment'. " +Original acc: 93.86%, attacked acc: 92.42%, dropped acc: 1.44% + +Original prompt: Acting as an entailment detection instrument, determine if the given pair of sentences demonstrates entailment or not_entailment. Answer with 'entailment' or 'not_entailment'. +Attacked prompt: b"Acting as an entailment detection instrument, determine if the given pair of sentences denotes entailment or not_entailment. Answer with 'entailment' or 'not_entailment'. " +Original acc: 93.50%, attacked acc: 92.78%, dropped acc: 0.72% + +Original prompt: As a tool for determining entailment relationships, review the two statements and categorize their connection as either 'entailment' or 'not_entailment'. +Attacked prompt: b"Because a device for determining entailment relationships, review the two words and categorize their connection as either 'entailment' or 'not_entailment'. " +Original acc: 93.50%, attacked acc: 91.34%, dropped acc: 2.17% + +## translation + +Language: chinese, acc: 93.14%, prompt: In the light of an implication analysis tool, evaluate the relationship between the following sentences and classify them as 'entailment' or 'not_entailment'. +Language: chinese, acc: 91.70%, prompt: From the perspective of an implication analysis tool, determine whether there is an implication relationship in the following sentences by classifying them as 'entailment' or 'not_entailment'. +Language: chinese, acc: 91.34%, prompt: Please use an implication analysis tool to determine whether an implication relationship exists in the following sentences by classifying them as 'entailment' or 'not_entailment'. +Language: chinese, acc: 93.14%, prompt: Please evaluate the relation of the following sentences as 'entailment' or 'not_entailment' for the purpose of determining implication relation. +Language: chinese, acc: 91.70%, prompt: Please use the implication analysis tool to evaluate the relationships between the following sentences and classify them as 'entailment' or 'not_entailment'. +Language: chinese, acc: 92.42%, prompt: For the purpose of determining implicative relations, analyze the relations of the following sentences and classify them as 'entailment' or 'not_entailment'. +Language: chinese, acc: 92.06%, prompt: Please use the implication analysis tool to determine the relationship of the following sentences and classify them as 'entailment' or 'not_entailment'. +Language: chinese, acc: 91.70%, prompt: Please use the implication judgment tool to assess the relevance of the following sentences and classify them as 'entailment' or 'not_entailment'. +Language: chinese, acc: 92.78%, prompt: Please, with implication analysis as the main task, determine the relationships between the following sentences and classify them as 'entailment' or 'not_entailment'. +Language: chinese, acc: 92.42%, prompt: Using the implication judgment as a criterion, analyze the relation of the following sentences and classify them as 'entailment' or 'not_entailment'. +Language: french, acc: 92.06%, prompt: As an engagement analysis tool, evaluate the relationship between the given sentences and classify it as 'entailment' or 'not_entailment'. +Language: french, acc: 92.42%, prompt: Determine whether the given sentences involve one another or not as an implication analysis tool. Classify them accordingly as 'entailment' or 'not_entailment'. +Language: french, acc: 92.06%, prompt: Using implication analysis, evaluate whether the sentences provided have a logical relationship and categorize them as 'entailment' or 'not_entailment'. +Language: french, acc: 93.50%, prompt: As an engagement assessment tool, determine whether the sentences provided have a logical relationship and classify them as 'entailment' or 'not_entailment'. +Language: french, acc: 91.70%, prompt: As an implication classification tool, analyze the sentences provided to determine if there is a logical relationship and categorize them as 'entailment' or 'not_entailment'. +Language: french, acc: 92.78%, prompt: Using implication analysis, determine whether the given sentences have a cause-effect relationship and categorize them as 'entailment' or 'not_entailment'. +Language: french, acc: 93.14%, prompt: Evaluate the relationship between the given sentences using implication analysis and rank them accordingly as 'entailment' or 'not_entailment'. +Language: french, acc: 92.42%, prompt: As an engagement detection tool, determine whether the given sentences have a logical relationship and categorize them as 'entailment' or 'not_entailment'. +Language: french, acc: 92.78%, prompt: Using implication analysis, evaluate whether the sentences provided have a cause-effect relationship and rank them accordingly as 'entailment' or 'not_entailment'. +Language: french, acc: 92.42%, prompt: Determine whether the given sentences have a cause-effect relationship as an engagement analysis tool and categorize them as 'entailment' or 'not_entailment'. +Language: arabic, acc: 92.42%, prompt: In your role as a tool for reasoning analysis, evaluate the relationship between given sentences and classify them as 'entailment' or 'not_entailment'. +Language: arabic, acc: 92.78%, prompt: Can you determine whether this sentence is inferred from the other sentence? Classify it as 'entailment' or 'not_entailment'. +Language: arabic, acc: 92.42%, prompt: Using the tool of reasoning analysis, analyze the relationship between given sentences and classify them as 'entailment' or 'not_entailment'. +Language: arabic, acc: 92.78%, prompt: Does this sentence represent a conclusion from the previous sentence? Classify it as 'entailment' or 'not_entailment'. +Language: arabic, acc: 91.70%, prompt: As a tool of reasoning analysis, evaluate the relationship of given sentences and classify them as 'entailment' or 'not_entailment'. +Language: arabic, acc: 92.78%, prompt: Can this sentence be inferred from the previous sentence? Classify it as 'entailment' or 'not_entailment'. +Language: arabic, acc: 92.42%, prompt: Using a tool to analyze a conclusion, analyze the relationship between the two sentences and classify them as 'entailment' or 'not_entailment'. +Language: arabic, acc: 92.78%, prompt: Is this a conclusion from the next sentence? Classify it as 'entailment' or 'not_entailment'. +Language: arabic, acc: 92.42%, prompt: As part of your task in analyzing a conclusion, evaluate the relationship between the two sentences and classify them as 'entailment' or 'not_entailment' based on their relationship. +Language: arabic, acc: 92.78%, prompt: Are you following this sentence directly from the previous one? Classify it as 'entailment' or 'not_entailment'. +Language: spanish, acc: 91.70%, prompt: In your role as an implication analysis tool, evaluate the relationship between the given phrases and classify them as 'entailment' or 'not_entailment'. +Language: spanish, acc: 93.86%, prompt: Determine whether the second sentence necessarily implies the first and label the relation as 'entailment', or as 'not_entailment' if not. +Language: spanish, acc: 92.78%, prompt: Classifies the relationship between these two sentences as 'entailment' if one necessarily implies the other, or as 'not_entailment' if not. +Language: spanish, acc: 93.14%, prompt: Evaluates whether the information in the second sentence is implied in the first and labels the relationship as 'entailment', or as 'not_entailment' if there is no such implication. +Language: spanish, acc: 92.78%, prompt: Given a couple of phrases, label their relationship as 'entailment' if one necessarily implies the other, or as 'not_entailment' if there is no such implication. +Language: spanish, acc: 92.06%, prompt: Analyzes the relationship between the phrases and classifies them as 'entailment' if one necessarily implies the other, or as 'not_entailment' if there is no such implication. +Language: spanish, acc: 93.14%, prompt: Given two sentences, determine whether the second sentence is a necessary consequence of the first and label the relation as 'entailment', or as 'not_entailment' if not. +Language: spanish, acc: 93.14%, prompt: Evaluates whether the information presented in the second sentence is implicit in the first and labels the relationship as 'entailment', or as 'not_entailment' if there is no such implication. +Language: spanish, acc: 93.14%, prompt: Classifies the relationship between the given phrases as 'entailment' if one necessarily implies the other, or as 'not_entailment' if there is no such implication. +Language: spanish, acc: 92.42%, prompt: Determines whether the information provided in the second sentence is necessarily inferable from the first and labels the relationship as 'entailment', or as 'not_entailment' if not. +Language: japanese, acc: 91.70%, prompt: Analyze the relationship of a given sentence and classify it as 'entailment' or 'not_entailment'. +Language: japanese, acc: 92.06%, prompt: Evaluate the semantic relationship of the sentence and classify it as 'entailment' or 'not_entailment'. +Language: japanese, acc: 92.78%, prompt: Please judge the relationship between the given sentences and classify them as 'entailment' or 'not_entailment'. +Language: japanese, acc: 90.97%, prompt: Examine the paraphrases of a given sentence and classify them 'entailment' or 'not_entailment'. +Language: japanese, acc: 91.70%, prompt: Rate the similarity of a given sentence and categorize it as 'entailment' or 'not_entailment'. +Language: japanese, acc: 91.34%, prompt: Determinate the semantic connections of a given sentence and classify it as 'entailment' or 'not_entailment'. +Language: japanese, acc: 90.61%, prompt: Examine the semantic match of a given sentence and categorize it as 'entailment' or 'not_entailment'. +Language: japanese, acc: 92.78%, prompt: Classify it as 'entailment' or 'not_entailment' based on the content of the sentence. +Language: japanese, acc: 91.70%, prompt: Analyze the relationship of a given sentence and classify it as 'entailment' or 'not_entailment'. +Language: japanese, acc: 91.34%, prompt: Judge the semantic connections of a given sentence and categorize it as 'entailment' or 'not_entailment'. +Language: korean, acc: 92.42%, prompt: Evaluate the relationship between any two sentences given to you and classify you as 'entailment' or 'not_entailment'. +Language: korean, acc: 92.42%, prompt: Analyze the semantic deductive relations between sentences and classify them as 'entailment' or 'not_entailment'. +Language: korean, acc: 93.14%, prompt: Evaluate the logical relevance between sentences and classify them as 'entailment' or 'not_entailment'. +Language: korean, acc: 93.14%, prompt: Evaluate the interaction of two given sentences and classify them as 'entailment' or 'not_entailment'. +Language: korean, acc: 93.14%, prompt: Please check whether there is a semantic match between those two sentences and classify them as 'entailment' or 'not_entailment'. +Language: korean, acc: 93.14%, prompt: Compare information between given sentences and classify them as 'entailment' or 'not_entailment'. +Language: korean, acc: 93.14%, prompt: Please analyse the correlation between those two sentences and classify them as 'entailment' or 'not_entailment'. +Language: korean, acc: 93.14%, prompt: Evaluate the different meanings between given sentences and classify them as 'entailment' or 'not_entailment'. +Language: korean, acc: 92.78%, prompt: Compare the semantic structure of the two sentences and classify them as 'entailment' or 'not_entailment'. +Language: korean, acc: 92.42%, prompt: Evaluate the interactions between sentences and classify them as 'entailment' or 'not_entailment'. + +# sst2 + +## 10 prompts + +Acc: 96.79%, prompt: Evaluate the sentiment of the given text and classify it as 'positive' or 'negative'. +Acc: 96.79%, prompt: Determine the overall sentiment of this sentence, categorizing it as 'positive' or 'negative'. +Acc: 96.79%, prompt: Read the provided excerpt and choose between 'positive' and 'negative' to describe its sentiment. +Acc: 96.79%, prompt: Review this statement and decide whether it has a 'positive' or 'negative' sentiment. +Acc: 96.67%, prompt: Analyze the tone of this statement and respond with either 'positive' or 'negative'. +Acc: 96.22%, prompt: Please identify the emotional tone of this passage: 'positive' or 'negative'? +Acc: 96.10%, prompt: Assess the mood of the following quote and determine if it's 'positive' or 'negative'. +Acc: 95.76%, prompt: Considering the given phrase, would you say it carries a 'positive' or 'negative' connotation? +Acc: 95.18%, prompt: Given the context of this text, indicate if the emotion conveyed is 'positive' or 'negative'. +Acc: 92.66%, prompt: After examining the following expression, label its emotion as either 'positive' or 'negative'. + +Acc: 96.90%, prompt: Working as a sentiment analyzer, please indicate if the following text is 'positive' or 'negative'. +Acc: 96.56%, prompt: As a sentiment classifier, determine whether the following text is 'positive' or 'negative'. +Acc: 96.56%, prompt: In the role of a sentiment analysis tool, respond with 'positive' or 'negative' to classify this statement. +Acc: 96.56%, prompt: Acting as a sentiment evaluator, identify if the given sentence is 'positive' or 'negative'. +Acc: 96.56%, prompt: Functioning as a sentiment identification tool, assess if the following expression is 'positive' or 'negative'. +Acc: 96.44%, prompt: In the capacity of a sentiment classifier, decide whether the given quote is 'positive' or 'negative'. +Acc: 96.44%, prompt: Serving as a sentiment evaluation model, determine if the given statement is 'positive' or 'negative'. +Acc: 96.44%, prompt: Emulating a sentiment classification system, indicate whether the provided text is 'positive' or 'negative'. +Acc: 95.87%, prompt: As an emotion detector, determine if the provided passage conveys a 'positive' or 'negative' sentiment. +Acc: 95.07%, prompt: Taking on the role of an emotion classifier, specify if the provided phrase is 'positive' or 'negative'. + +## bertattack + +Original prompt: Read the provided excerpt and choose between 'positive' and 'negative' to describe its sentiment. +Attacked prompt: b"search the provided excerpt and play between 'positive' and 'negative' to describe its mood. " +Original acc: 96.90%, attacked acc: 96.10%, dropped acc: 0.80% + +Original prompt: Evaluate the sentiment of the given text and classify it as 'positive' or 'negative'. +Attacked prompt: b"assess the sentiment of the given language and classify it as 'positive' or 'negative'. " +Original acc: 96.79%, attacked acc: 95.64%, dropped acc: 1.15% + +Original prompt: Determine the overall sentiment of this sentence, categorizing it as 'positive' or 'negative'. +Attacked prompt: b"locate the associate emotion of this sentence, categorizing it as 'positive' or 'negative'. " +Original acc: 96.79%, attacked acc: 92.20%, dropped acc: 4.59% + +Original prompt: Working as a sentiment analyzer, please indicate if the following text is 'positive' or 'negative'. +Attacked prompt: b"Working as a emotion analyzer, please sort if the cross text is 'positive' or 'negative'. " +Original acc: 96.67%, attacked acc: 95.64%, dropped acc: 1.03% + +Original prompt: As a sentiment classifier, determine whether the following text is 'positive' or 'negative'. +Attacked prompt: b"in a sentiment classifier, determine where the over words is 'positive' or 'negative'. " +Original acc: 96.56%, attacked acc: 95.30%, dropped acc: 1.26% + +Original prompt: In the role of a sentiment analysis tool, respond with 'positive' or 'negative' to classify this statement. +Attacked prompt: b"when the role of a sentiment analysis instrument, responding with 'positive' or 'negative' to contrast this statement. " +Original acc: 96.56%, attacked acc: 95.87%, dropped acc: 0.69% + +## checklist + +Original prompt: Evaluate the sentiment of the given text and classify it as 'positive' or 'negative'. +Attacked prompt: b"Evaluate the sentiment of the given text and classify it as 'positive' or 'negative' Cev0s49fbe. " +Original acc: 96.79%, attacked acc: 96.56%, dropped acc: 0.23% + +Original prompt: Determine the overall sentiment of this sentence, categorizing it as 'positive' or 'negative'. +Attacked prompt: b"Determine the overall sentiment of this sentence, categorizing it as 'positive' or 'negative' MSAddJ4D2a. " +Original acc: 96.79%, attacked acc: 96.67%, dropped acc: 0.11% + +Original prompt: Read the provided excerpt and choose between 'positive' and 'negative' to describe its sentiment. +Attacked prompt: b"Read the provided excerpt and choose between 'positive' and 'negative' to describe its sentiment SvAp8RlOFn. " +Original acc: 96.79%, attacked acc: 96.67%, dropped acc: 0.11% + +Original prompt: Working as a sentiment analyzer, please indicate if the following text is 'positive' or 'negative'. +Attacked prompt: b"Working as a sentiment analyzer, please indicate if the following text is 'positive' or 'negative' MSAddJ4D2a. " +Original acc: 96.90%, attacked acc: 96.56%, dropped acc: 0.34% + +Original prompt: As a sentiment classifier, determine whether the following text is 'positive' or 'negative'. +Attacked prompt: b"As a sentiment classifier, determine whether the following text is 'positive' or 'negative' 6a4Yn3RGVc. " +Original acc: 96.56%, attacked acc: 96.44%, dropped acc: 0.11% + +Original prompt: In the role of a sentiment analysis tool, respond with 'positive' or 'negative' to classify this statement. +Attacked prompt: b"In the role of a sentiment analysis tool, respond with 'positive' or 'negative' to classify this statement 6a4Yn3RGVc. " +Original acc: 96.56%, attacked acc: 96.67%, dropped acc: -0.11% + +## deepwordbug + +Original prompt: Evaluate the sentiment of the given text and classify it as 'positive' or 'negative'. +Attacked prompt: b"Evaluate the sentiment of the given tXxt and classify it as 'positive' or 'negative'. " +Original acc: 96.79%, attacked acc: 96.33%, dropped acc: 0.46% + +Original prompt: Determine the overall sentiment of this sentence, categorizing it as 'positive' or 'negative'. +Attacked prompt: b"Determine the ovreall sentiment of this sentence, categorizing it as 'positive' or 'negative'. " +Original acc: 96.79%, attacked acc: 96.67%, dropped acc: 0.11% + +Original prompt: Read the provided excerpt and choose between 'positive' and 'negative' to describe its sentiment. +Attacked prompt: b"Read the provided excerpt and choose between 'positive' and 'negative' to describe its sentiment. " +Original acc: 96.79%, attacked acc: 96.79%, dropped acc: 0.00% + +Original prompt: Working as a sentiment analyzer, please indicate if the following text is 'positive' or 'negative'. +Attacked prompt: b"Working as a sentiment analyzer, Jlease findicate if the followign text is 'positive' or 'negative'. " +Original acc: 96.90%, attacked acc: 96.22%, dropped acc: 0.69% + +Original prompt: As a sentiment classifier, determine whether the following text is 'positive' or 'negative'. +Attacked prompt: b"As a sentiment classifier, determine whether the followJing text is 'positive' or 'negative'. " +Original acc: 96.56%, attacked acc: 96.10%, dropped acc: 0.46% + +Original prompt: In the role of a sentiment analysis tool, respond with 'positive' or 'negative' to classify this statement. +Attacked prompt: b"In the role of a sentiment analysis tool, respond with 'positive' or 'negative' to classify this statement. " +Original acc: 96.56%, attacked acc: 96.56%, dropped acc: 0.00% + +## stresstest + +Original prompt: Evaluate the sentiment of the given text and classify it as 'positive' or 'negative'. +Attacked prompt: b"Evaluate the sentiment of the given text and classify it as 'positive' or 'negative' and false is not true . " +Original acc: 96.79%, attacked acc: 96.79%, dropped acc: 0.00% + +Original prompt: Determine the overall sentiment of this sentence, categorizing it as 'positive' or 'negative'. +Attacked prompt: b"Determine the overall sentiment of this sentence, categorizing it as 'positive' or 'negative' and false is not true . " +Original acc: 96.79%, attacked acc: 96.67%, dropped acc: 0.11% + +Original prompt: Read the provided excerpt and choose between 'positive' and 'negative' to describe its sentiment. +Attacked prompt: b"Read the provided excerpt and choose between 'positive' and 'negative' to describe its sentiment and true is true . " +Original acc: 96.79%, attacked acc: 96.67%, dropped acc: 0.11% + +Original prompt: Working as a sentiment analyzer, please indicate if the following text is 'positive' or 'negative'. +Attacked prompt: b"Working as a sentiment analyzer, please indicate if the following text is 'positive' or 'negative' and false is not true . " +Original acc: 96.90%, attacked acc: 96.67%, dropped acc: 0.23% + +Original prompt: As a sentiment classifier, determine whether the following text is 'positive' or 'negative'. +Attacked prompt: b"As a sentiment classifier, determine whether the following text is 'positive' or 'negative' and false is not true . " +Original acc: 96.56%, attacked acc: 96.33%, dropped acc: 0.23% + +Original prompt: In the role of a sentiment analysis tool, respond with 'positive' or 'negative' to classify this statement. +Attacked prompt: b"In the role of a sentiment analysis tool, respond with 'positive' or 'negative' to classify this statement and true is true and true is true and true is true and true is true and true is true . " +Original acc: 96.56%, attacked acc: 96.56%, dropped acc: 0.00% + +## textbugger + +Original prompt: Evaluate the sentiment of the given text and classify it as 'positive' or 'negative'. +Attacked prompt: b"Evalu ate the sentiment of the given text and classify it as 'positive' or 'negative'. " +Original acc: 96.79%, attacked acc: 96.56%, dropped acc: 0.23% + +Original prompt: Determine the overall sentiment of this sentence, categorizing it as 'positive' or 'negative'. +Attacked prompt: b"Determine the general sentiment of this condemnation, categorizing it as 'positive' or 'negative'. " +Original acc: 96.79%, attacked acc: 95.87%, dropped acc: 0.92% + +Original prompt: Read the provided excerpt and choose between 'positive' and 'negative' to describe its sentiment. +Attacked prompt: b"Maltese the provided excerpt and choose between 'positive' and 'negative' to describe its sentiment. " +Original acc: 96.79%, attacked acc: 96.67%, dropped acc: 0.11% + +Original prompt: Working as a sentiment analyzer, please indicate if the following text is 'positive' or 'negative'. +Attacked prompt: b"Working as a mood analyzer, invites ind icate if the following text is 'positive' or 'negative'. " +Original acc: 96.79%, attacked acc: 96.10%, dropped acc: 0.69% + +Original prompt: In the role of a sentiment analysis tool, respond with 'positive' or 'negative' to classify this statement. +Attacked prompt: b"In the role of a emotion analysis tool, r\xd0\xb5spond with 'positive' or 'negative' to classify this statement. " +Original acc: 96.67%, attacked acc: 96.10%, dropped acc: 0.57% + +Original prompt: As a sentiment classifier, determine whether the following text is 'positive' or 'negative'. +Attacked prompt: b"As a emotion classifier, determine whether the foll\xd0\xbewing wording is 'positive' or 'negative'. " +Original acc: 96.56%, attacked acc: 95.18%, dropped acc: 1.38% + +## textfooler + +Original prompt: Evaluate the sentiment of the given text and classify it as 'positive' or 'negative'. +Attacked prompt: b"Measured the emotion of the handed text and classify it as 'positive' or 'negative'. " +Original acc: 96.79%, attacked acc: 95.18%, dropped acc: 1.61% + +Original prompt: Determine the overall sentiment of this sentence, categorizing it as 'positive' or 'negative'. +Attacked prompt: b"Determine the plenary senses of this condemning, categorizing it as 'positive' or 'negative'. " +Original acc: 96.79%, attacked acc: 93.46%, dropped acc: 3.33% + +Original prompt: Read the provided excerpt and choose between 'positive' and 'negative' to describe its sentiment. +Attacked prompt: b"Lire the rendered excerpt and choose between 'positive' and 'negative' to identifies its emotion. " +Original acc: 96.79%, attacked acc: 94.61%, dropped acc: 2.18% + +Original prompt: Working as a sentiment analyzer, please indicate if the following text is 'positive' or 'negative'. +Attacked prompt: b"Working as a emotion analyzer, please demonstrates if the following texts is 'positive' or 'negative'. " +Original acc: 96.79%, attacked acc: 96.10%, dropped acc: 0.69% + +Original prompt: In the role of a sentiment analysis tool, respond with 'positive' or 'negative' to classify this statement. +Attacked prompt: b"In the role of a emotion analysis tool, respond with 'positive' or 'negative' to classify this languages. " +Original acc: 96.67%, attacked acc: 95.64%, dropped acc: 1.03% + +Original prompt: As a sentiment classifier, determine whether the following text is 'positive' or 'negative'. +Attacked prompt: b"As a emotion classifier, ascertain whether the suite wording is 'positive' or 'negative'. " +Original acc: 96.56%, attacked acc: 95.18%, dropped acc: 1.38% + +## translation + +Language: chinese, acc: 96.79%, prompt: Answer whether the statement is 'positive' or 'negative' based on sentiment analysis. +Language: chinese, acc: 94.38%, prompt: As an emotion analysis tool, determine whether the emotion in the text is 'positive' or 'negative'. +Language: chinese, acc: 96.44%, prompt: Categorize the statement as 'positive' or 'negative', based on its emotional bent. +Language: chinese, acc: 96.44%, prompt: Please use sentiment analysis to classify the text as 'positive' or 'negative'. +Language: chinese, acc: 94.38%, prompt: Please determine whether the emotion of the sentence is 'positive' or 'negative' and categorize it. +Language: chinese, acc: 96.67%, prompt: Using sentiment analysis, classify the text as 'positive' or 'negative'. +Language: chinese, acc: 94.38%, prompt: Please answer whether the emotion of the sentence is 'positive' or 'negative' and categorize it. +Language: chinese, acc: 96.79%, prompt: Categorize the statement as 'positive' or 'negative' based on sentiment analysis. +Language: chinese, acc: 96.67%, prompt: Please judge this text as 'positive' or 'negative' according to the criteria of sentiment analysis. +Language: chinese, acc: 95.64%, prompt: Please classify this sentence as 'positive' or 'negative' according to the principles of emotion analysis. +Language: french, acc: 96.67%, prompt: As a sentiment analysis tool, please answer with 'positive' or 'negative' to classify this statement. +Language: french, acc: 96.33%, prompt: Determine whether this phrase is 'positive' or 'negative' as a sentiment classification tool. +Language: french, acc: 96.79%, prompt: Identify the tone of this statement by choosing between 'positive' and 'negative' as a sentiment analysis tool. +Language: french, acc: 96.79%, prompt: Use sentiment analysis to classify this statement as 'positive' or 'negative'. +Language: french, acc: 96.56%, prompt: As a sentiment classification tool, please determine whether this statement is 'positive' or 'negative'. +Language: french, acc: 96.67%, prompt: Classify this sentence as 'positive' or 'negative' using sentiment analysis. +Language: french, acc: 96.79%, prompt: Choose between 'positive' or 'negative' to classify this statement as a sentiment analysis tool. +Language: french, acc: 96.79%, prompt: Identify the sentiment expressed in this statement by selecting 'positive' or 'negative' as a sentiment classification tool. +Language: french, acc: 96.79%, prompt: Determine whether this phrase is 'positive' or 'negative' using sentiment analysis as a classification tool. +Language: french, acc: 96.79%, prompt: Use sentiment analysis to classify this statement as 'positive' or 'negative'. +Language: arabic, acc: 96.33%, prompt: Under emotional analysis, answer 'positive' or 'negative' to classify this statement. +Language: arabic, acc: 96.67%, prompt: Does this statement express a 'positive' or 'negative' reaction? +Language: arabic, acc: 96.33%, prompt: Is that a 'positive' or a 'negative' phrase? +Language: arabic, acc: 97.02%, prompt: What is the classification between 'positive' and 'negative'? +Language: arabic, acc: 96.56%, prompt: Does this sentence express 'positive' or 'negative' feelings? +Language: arabic, acc: 96.79%, prompt: In the context of textual analysis, what classification is this phrase between 'positive' and 'negative'? +Language: arabic, acc: 96.79%, prompt: Could this be classified as 'positive' or 'negative'? +Language: arabic, acc: 96.33%, prompt: In the context of emotional analysis, what classification is this statement between 'positive' and 'negative'? +Language: arabic, acc: 96.79%, prompt: Can this be classified as 'positive' or 'negative'? +Language: arabic, acc: 95.18%, prompt: Under the classification of emotions, is this sentence 'positive' or 'negative'? +Language: spanish, acc: 96.67%, prompt: As a feeling analysis tool, classify this statement as 'positive' or 'negative'. +Language: spanish, acc: 96.44%, prompt: Determine whether this statement has a 'positive' or 'negative' connotation. +Language: spanish, acc: 96.90%, prompt: Indicate whether the following statement is 'positive' or 'negative'. +Language: spanish, acc: 95.87%, prompt: Evaluate whether this text has a 'positive' or 'negative' emotional charge. +Language: spanish, acc: 96.67%, prompt: According to your sentiment analysis, would you say this comment is 'positive' or 'negative'? +Language: spanish, acc: 96.67%, prompt: In the context of sentiment analysis, label this sentence as 'positive' or 'negative'. +Language: spanish, acc: 96.90%, prompt: Rate the following statement as 'positive' or 'negative', according to your sentiment analysis. +Language: spanish, acc: 96.22%, prompt: How would you classify this text in terms of its emotional tone? 'positive' or 'negative'? +Language: spanish, acc: 96.67%, prompt: As a tool for sentiment analysis, would you say this statement is 'positive' or 'negative'? +Language: spanish, acc: 96.90%, prompt: Classify this statement as 'positive' or 'negative', please. +Language: japanese, acc: 95.30%, prompt: Treat this sentence as an emotion analysis tool and categorize it as 'positive' and 'negative'. +Language: japanese, acc: 96.79%, prompt: Use this article as a sentiment analysis tool to classify 'positive' and 'negative'. +Language: japanese, acc: 95.53%, prompt: Use this sentence as an emotion analysis tool to determine whether it is 'positive' or 'negative'. +Language: japanese, acc: 95.07%, prompt: Use this sentence as an emotion analysis tool to classify 'positive' and 'negative'. +Language: japanese, acc: 96.56%, prompt: Use this sentence as a sentiment analysis tool and classify it as 'positive' or 'negative'. +Language: japanese, acc: 96.67%, prompt: To classify this sentence as 'positive' or 'negative', evaluate it as a sentiment analysis tool. +Language: japanese, acc: 95.76%, prompt: Treat this sentence as an emotion analysis tool to determine whether it is 'positive' or 'negative'. +Language: japanese, acc: 96.56%, prompt: Use this sentence as a sentiment analysis tool to classify 'positive' and 'negative'. +Language: japanese, acc: 95.30%, prompt: Analyze this sentence as an emotion analysis tool to classify whether it is 'positive' or 'negative'. +Language: japanese, acc: 95.76%, prompt: Use this sentence as an emotional analysis tool to determine whether it is 'positive' or 'negative'. +Language: korean, acc: 96.10%, prompt: As an emotional analysis tool, respond with 'positive' or 'negative' to classify these sentences. +Language: korean, acc: 96.79%, prompt: Classify this sentence as 'positive' if you regard it as positive, 'negative' if you regard it as negative. +Language: korean, acc: 95.30%, prompt: Please rate the emotion of this sentence and classify it as 'positive' or 'negative'. +Language: korean, acc: 97.02%, prompt: Classify this sentence as 'positive' if you perceive it positively and 'negative' if you perceive it negatively. +Language: korean, acc: 96.56%, prompt: If this is a sentence delivered using a positive expression, classify it as 'positive' and if this is a sentence delivered using a negative expression, classify it as 'negative'. +Language: korean, acc: 96.67%, prompt: Respond with 'positive' or 'negative' by categorizing whether the sentence is positive or negative. +Language: korean, acc: 94.38%, prompt: Please analyze the emotion in this sentence and classify it as 'positive' or 'negative'. +Language: korean, acc: 96.56%, prompt: Classify this sentence as 'positive' if it contains a positive meaning, 'negative' if it contains a negative meaning. +Language: korean, acc: 96.56%, prompt: Classify this sentence as 'positive' if it contains positive content, 'negative' if it contains negative content. +Language: korean, acc: 96.56%, prompt: Classify what you're trying to convey in this sentence as 'positive' if it's positive, and 'negative' if it's negative. + +# wnli + +## 10 prompts + +Acc: 77.46%, prompt: Assess the connection between the following sentences and classify it as 'entailment' or 'not_entailment'. +Acc: 77.46%, prompt: Please classify the relationship between the provided sentences as 'entailment' or 'not_entailment'. +Acc: 77.46%, prompt: Indicate if the connection between the following sentences is 'entailment' or 'not_entailment'. +Acc: 76.06%, prompt: Are the following two sentences entailment or not_entailment? Answer me with "entailment" or "not_entailment", just one word. +Acc: 76.06%, prompt: Does the relationship between the given sentences represent entailment or not_entailment? Respond with 'entailment' or 'not_entailment'. +Acc: 76.06%, prompt: Examine the pair of sentences and determine if they exhibit entailment or not_entailment. Answer with either 'entailment' or 'not_entailment'. +Acc: 76.06%, prompt: Analyze the two provided sentences and decide if their relationship is 'entailment' or 'not_entailment'. +Acc: 76.06%, prompt: Identify whether the given pair of sentences demonstrates entailment or not_entailment. Answer with 'entailment' or 'not_entailment'. +Acc: 76.06%, prompt: Review the two statements and categorize their relationship as either 'entailment' or 'not_entailment'. +Acc: 76.06%, prompt: Determine if the given pair of sentences displays entailment or not_entailment. Respond with 'entailment' or 'not_entailment'. +Acc: 76.06%, prompt: Considering the two sentences, identify if their relationship is 'entailment' or 'not_entailment'. + +Acc: 77.46%, prompt: Working as an entailment classifier, identify whether the given pair of sentences displays entailment or not_entailment. Respond with 'entailment' or 'not_entailment'. +Acc: 76.06%, prompt: In your role as an entailment analysis tool, assess the relationship between the given sentences and classify it as 'entailment' or 'not_entailment'. +Acc: 76.06%, prompt: As an entailment identification system, examine the connection between the following sentences and respond with 'entailment' or 'not_entailment'. +Acc: 76.06%, prompt: Functioning as an entailment evaluation tool, analyze the provided sentences and decide if their relationship is 'entailment' or 'not_entailment'. +Acc: 76.06%, prompt: Acting as an entailment detection instrument, determine if the given pair of sentences demonstrates entailment or not_entailment. Answer with 'entailment' or 'not_entailment'. +Acc: 76.06%, prompt: As a tool for determining entailment relationships, review the two statements and categorize their connection as either 'entailment' or 'not_entailment'. +Acc: 76.06%, prompt: While performing entailment analysis, classify the relationship between the provided sentences as 'entailment' or 'not_entailment'. +Acc: 76.06%, prompt: In the capacity of an entailment assessment system, indicate if the link between the following sentences is 'entailment' or 'not_entailment'. +Acc: 76.06%, prompt: As an instrument for entailment evaluation, consider the two sentences and determine if their relationship is 'entailment' or 'not_entailment'. Respond with 'entailment' or 'not_entailment'. +Acc: 76.06%, prompt: In the role of a semantic relationship analyzer, examine the connection between the given sentences and decide if they exhibit entailment or not_entailment. Answer with 'entailment' or 'not_entailment'. + +## bertattack + +Original prompt: Assess the connection between the following sentences and classify it as 'entailment' or 'not_entailment'. +Attacked prompt: b"a the links between the following sentences and classify it as 'entailment' or 'not_entailment'. " +Original acc: 77.46%, attacked acc: 74.65%, dropped acc: 2.82% + +Original prompt: Please classify the relationship between the provided sentences as 'entailment' or 'not_entailment'. +Attacked prompt: b"Please address the relationship between the provided sentences as 'entailment' or 'not_entailment'. " +Original acc: 77.46%, attacked acc: 76.06%, dropped acc: 1.41% + +Original prompt: Indicate if the connection between the following sentences is 'entailment' or 'not_entailment'. +Attacked prompt: b"Indicate if the affiliation between the following sentences is 'entailment' or 'not_entailment'. " +Original acc: 77.46%, attacked acc: 76.06%, dropped acc: 1.41% + +Original prompt: Working as an entailment classifier, identify whether the given pair of sentences displays entailment or not_entailment. Respond with 'entailment' or 'not_entailment'. +Attacked prompt: b"Working as an entailment classauxiliary, identify but the verbal a of nouns displays entailment or not_entailment. Respond with 'entailment' or 'not_entailment'. " +Original acc: 77.46%, attacked acc: 66.20%, dropped acc: 11.27% + +Original prompt: In your role as an entailment analysis tool, assess the relationship between the given sentences and classify it as 'entailment' or 'not_entailment'. +Attacked prompt: b"In your role as an entailment analysis tool, assess the conversation between the verbal sentences and classify it as 'entailment' or 'not_entailment'. " +Original acc: 76.06%, attacked acc: 70.42%, dropped acc: 5.63% + +Original prompt: As an entailment identification system, examine the connection between the following sentences and respond with 'entailment' or 'not_entailment'. +Attacked prompt: b"As an entailment verbal system, examine the connection between the following sentences and respond with 'entailment' or 'not_entailment'. " +Original acc: 76.06%, attacked acc: 74.65%, dropped acc: 1.41% + +## checklist + +Original prompt: Assess the connection between the following sentences and classify it as 'entailment' or 'not_entailment'. +Attacked prompt: b"Assess the connection between the following sentences and classify it as 'entailment' or 'not_entailment' 5yWbBXztUY. " +Original acc: 77.46%, attacked acc: 76.06%, dropped acc: 1.41% + +Original prompt: Please classify the relationship between the provided sentences as 'entailment' or 'not_entailment'. +Attacked prompt: b"Please classify the relationship between the provided sentences as 'entailment' or 'not_entailment' g0vBZf3tQC. " +Original acc: 77.46%, attacked acc: 76.06%, dropped acc: 1.41% + +Original prompt: Indicate if the connection between the following sentences is 'entailment' or 'not_entailment'. +Attacked prompt: b"Indicate if the connection between the following sentences is 'entailment' or 'not_entailment' 5XeflW1ZJc. " +Original acc: 77.46%, attacked acc: 76.06%, dropped acc: 1.41% + +Original prompt: Working as an entailment classifier, identify whether the given pair of sentences displays entailment or not_entailment. Respond with 'entailment' or 'not_entailment'. +Attacked prompt: b"Working as an entailment classifier, identify whether the given pair of sentences displays entailment or not_entailment. Respond with 'entailment' or 'not_entailment' 5XeflW1ZJc. " +Original acc: 77.46%, attacked acc: 77.46%, dropped acc: 0.00% + +Original prompt: In your role as an entailment analysis tool, assess the relationship between the given sentences and classify it as 'entailment' or 'not_entailment'. +Attacked prompt: b"In your role as an entailment analysis tool, assess the relationship between the given sentences and classify it as 'entailment' or 'not_entailment' 5XeflW1ZJc. " +Original acc: 76.06%, attacked acc: 76.06%, dropped acc: 0.00% + +Original prompt: As an entailment identification system, examine the connection between the following sentences and respond with 'entailment' or 'not_entailment'. +Attacked prompt: b"As an entailment identification system, examine the connection between the following sentences and respond with 'entailment' or 'not_entailment' 5XeflW1ZJc. " +Original acc: 76.06%, attacked acc: 76.06%, dropped acc: 0.00% + +## deepwordbug + +Original prompt: Assess the connection between the following sentences and classify it as 'entailment' or 'not_entailment'. +Attacked prompt: b"Assuss the connection between the following sensences and classify it as 'entailment' or 'not_entailment'. " +Original acc: 77.46%, attacked acc: 74.65%, dropped acc: 2.82% + +Original prompt: Please classify the relationship between the provided sentences as 'entailment' or 'not_entailment'. +Attacked prompt: b"Please classify the relationNship between the provided sentences as 'entailment' or 'not_entailment'. " +Original acc: 77.46%, attacked acc: 74.65%, dropped acc: 2.82% + +Original prompt: Indicate if the connection between the following sentences is 'entailment' or 'not_entailment'. +Attacked prompt: b"Indicate if the conection between the following sentences is 'entailment' or 'not_entailment'. " +Original acc: 77.46%, attacked acc: 76.06%, dropped acc: 1.41% + +Original prompt: Working as an entailment classifier, identify whether the given pair of sentences displays entailment or not_entailment. Respond with 'entailment' or 'not_entailment'. +Attacked prompt: b"Working as an entailment classifeir, identify whether the given pair of sentences displays entailment or not_entailment. Respond with 'entailment' or 'not_entailment'. " +Original acc: 77.46%, attacked acc: 76.06%, dropped acc: 1.41% + +Original prompt: In your role as an entailment analysis tool, assess the relationship between the given sentences and classify it as 'entailment' or 'not_entailment'. +Attacked prompt: b"In your role as an entailment analysis tool, assess the relationship between the given sentences and classify it as 'entailment' or 'not_entailment'. " +Original acc: 76.06%, attacked acc: 76.06%, dropped acc: 1.41% + +Original prompt: As an entailment identification system, examine the connection between the following sentences and respond with 'entailment' or 'not_entailment'. +Attacked prompt: b"As an entailment identification system, examine the connection between the following sentences and respond with 'entailment' or 'not_entailment'. " +Original acc: 76.06%, attacked acc: 76.06%, dropped acc: 0.00% + +## stresstest + +Original prompt: Assess the connection between the following sentences and classify it as 'entailment' or 'not_entailment'. +Attacked prompt: b"Assess the connection between the following sentences and classify it as 'entailment' or 'not_entailment' and false is not true . " +Original acc: 77.46%, attacked acc: 76.06%, dropped acc: 1.41% + +Original prompt: Please classify the relationship between the provided sentences as 'entailment' or 'not_entailment'. +Attacked prompt: b"Please classify the relationship between the provided sentences as 'entailment' or 'not_entailment' and false is not true . " +Original acc: 77.46%, attacked acc: 74.65%, dropped acc: 2.82% + +Original prompt: Indicate if the connection between the following sentences is 'entailment' or 'not_entailment'. +Attacked prompt: b"Indicate if the connection between the following sentences is 'entailment' or 'not_entailment' and false is not true . " +Original acc: 77.46%, attacked acc: 74.65%, dropped acc: 2.82% + +Original prompt: Working as an entailment classifier, identify whether the given pair of sentences displays entailment or not_entailment. Respond with 'entailment' or 'not_entailment'. +Attacked prompt: b"Working as an entailment classifier, identify whether the given pair of sentences displays entailment or not_entailment. Respond with 'entailment' or 'not_entailment' and false is not true . " +Original acc: 77.46%, attacked acc: 76.06%, dropped acc: 1.41% + +Original prompt: In your role as an entailment analysis tool, assess the relationship between the given sentences and classify it as 'entailment' or 'not_entailment'. +Attacked prompt: b"In your role as an entailment analysis tool, assess the relationship between the given sentences and classify it as 'entailment' or 'not_entailment' and false is not true . " +Original acc: 76.06%, attacked acc: 74.65%, dropped acc: 1.41% + +Original prompt: As an entailment identification system, examine the connection between the following sentences and respond with 'entailment' or 'not_entailment'. +Attacked prompt: b"As an entailment identification system, examine the connection between the following sentences and respond with 'entailment' or 'not_entailment' and false is not true . " +Original acc: 76.06%, attacked acc: 76.06%, dropped acc: 0.00% + +## textbugger + +Original prompt: Assess the connection between the following sentences and classify it as 'entailment' or 'not_entailment'. +Attacked prompt: b"Assss the connection between the following sentences and classify it as 'entailment' or 'not_entailment'. " +Original acc: 77.46%, attacked acc: 76.06%, dropped acc: 1.41% + +Original prompt: Please classify the relationship between the provided sentences as 'entailment' or 'not_entailment'. +Attacked prompt: b"Please cassify the relationship between the provided sentences as 'entailment' or 'not_entailment'. " +Original acc: 77.46%, attacked acc: 76.06%, dropped acc: 1.41% + +Original prompt: Indicate if the connection between the following sentences is 'entailment' or 'not_entailment'. +Attacked prompt: b"Indicate if the con nection between the following sentences is 'entailment' or 'not_entailment'. " +Original acc: 77.46%, attacked acc: 76.06%, dropped acc: 1.41% + +Original prompt: Working as an entailment classifier, identify whether the given pair of sentences displays entailment or not_entailment. Respond with 'entailment' or 'not_entailment'. +Attacked prompt: b"Working as an entailment cla ssifier, identify whether the given pair of punishments displays entailment or not_entailment. Respond with 'entailment' or 'not_entailment'. " +Original acc: 77.46%, attacked acc: 74.65%, dropped acc: 2.82% + +Original prompt: In your role as an entailment analysis tool, assess the relationship between the given sentences and classify it as 'entailment' or 'not_entailment'. +Attacked prompt: b"In your role as an entailment analysis tool, assess the relationship between the given punishments and categorize it as 'entailment' or 'not_entailment'. " +Original acc: 76.06%, attacked acc: 71.83%, dropped acc: 4.23% + +Original prompt: As an entailment identification system, examine the connection between the following sentences and respond with 'entailment' or 'not_entailment'. +Attacked prompt: b"As an entailment identification system, examine the connection between the following sentences and respond with 'entailment' or 'not_entailment'. " +Original acc: 76.06%, attacked acc: 76.06%, dropped acc: 0.00% + +## textfooler + +Original prompt: Assess the connection between the following sentences and classify it as 'entailment' or 'not_entailment'. +Attacked prompt: b"Appraisal the attach between the suite condemns and classify it as 'entailment' or 'not_entailment'. " +Original acc: 77.46%, attacked acc: 73.24%, dropped acc: 4.23% + +Original prompt: Please classify the relationship between the provided sentences as 'entailment' or 'not_entailment'. +Attacked prompt: b"Please hierarchy the relationship between the provided punishment as 'entailment' or 'not_entailment'. " +Original acc: 77.46%, attacked acc: 74.65%, dropped acc: 2.82% + +Original prompt: Indicate if the connection between the following sentences is 'entailment' or 'not_entailment'. +Attacked prompt: b"Indicate if the login between the following sentences is 'entailment' or 'not_entailment'. " +Original acc: 77.46%, attacked acc: 74.65%, dropped acc: 2.82% + +Original prompt: Working as an entailment classifier, identify whether the given pair of sentences displays entailment or not_entailment. Respond with 'entailment' or 'not_entailment'. +Attacked prompt: b"Working as an entailment classifier, identify whether the given couple of condemnation displays entailment or not_entailment. Respond with 'entailment' or 'not_entailment'. " +Original acc: 77.46%, attacked acc: 74.65%, dropped acc: 2.82% + +Original prompt: In your role as an entailment analysis tool, assess the relationship between the given sentences and classify it as 'entailment' or 'not_entailment'. +Attacked prompt: b"In your role as an entailment analysis tool, assess the reports between the given sentences and classify it as 'entailment' or 'not_entailment'. " +Original acc: 76.06%, attacked acc: 73.24%, dropped acc: 2.82% + +Original prompt: As an entailment identification system, examine the connection between the following sentences and respond with 'entailment' or 'not_entailment'. +Attacked prompt: b"As an entailment identification system, examine the connection between the following sentences and respond with 'entailment' or 'not_entailment'. " +Original acc: 76.06%, attacked acc: 76.06%, dropped acc: 0.00% + +## translation + +Language: chinese, acc: 77.46%, prompt: In the light of an implication analysis tool, evaluate the relationship between the following sentences and classify them as 'entailment' or 'not_entailment'. +Language: chinese, acc: 76.06%, prompt: From the perspective of an implication analysis tool, determine whether there is an implication relationship in the following sentences by classifying them as 'entailment' or 'not_entailment'. +Language: chinese, acc: 76.06%, prompt: Please use an implication analysis tool to determine whether an implication relationship exists in the following sentences by classifying them as 'entailment' or 'not_entailment'. +Language: chinese, acc: 76.06%, prompt: Please evaluate the relation of the following sentences as 'entailment' or 'not_entailment' for the purpose of determining implication relation. +Language: chinese, acc: 77.46%, prompt: Please use the implication analysis tool to evaluate the relationships between the following sentences and classify them as 'entailment' or 'not_entailment'. +Language: chinese, acc: 74.65%, prompt: For the purpose of determining implicative relations, analyze the relations of the following sentences and classify them as 'entailment' or 'not_entailment'. +Language: chinese, acc: 77.46%, prompt: Please use the implication analysis tool to determine the relationship of the following sentences and classify them as 'entailment' or 'not_entailment'. +Language: chinese, acc: 76.06%, prompt: Please use the implication judgment tool to assess the relevance of the following sentences and classify them as 'entailment' or 'not_entailment'. +Language: chinese, acc: 77.46%, prompt: Please, with implication analysis as the main task, determine the relationships between the following sentences and classify them as 'entailment' or 'not_entailment'. +Language: chinese, acc: 76.06%, prompt: Using the implication judgment as a criterion, analyze the relation of the following sentences and classify them as 'entailment' or 'not_entailment'. +Language: french, acc: 77.46%, prompt: As an engagement analysis tool, evaluate the relationship between the given sentences and classify it as 'entailment' or 'not_entailment'. +Language: french, acc: 76.06%, prompt: Determine whether the given sentences involve one another or not as an implication analysis tool. Classify them accordingly as 'entailment' or 'not_entailment'. +Language: french, acc: 76.06%, prompt: Using implication analysis, evaluate whether the sentences provided have a logical relationship and categorize them as 'entailment' or 'not_entailment'. +Language: french, acc: 77.46%, prompt: As an engagement assessment tool, determine whether the sentences provided have a logical relationship and classify them as 'entailment' or 'not_entailment'. +Language: french, acc: 76.06%, prompt: As an implication classification tool, analyze the sentences provided to determine if there is a logical relationship and categorize them as 'entailment' or 'not_entailment'. +Language: french, acc: 74.65%, prompt: Using implication analysis, determine whether the given sentences have a cause-effect relationship and categorize them as 'entailment' or 'not_entailment'. +Language: french, acc: 77.46%, prompt: Evaluate the relationship between the given sentences using implication analysis and rank them accordingly as 'entailment' or 'not_entailment'. +Language: french, acc: 77.46%, prompt: As an engagement detection tool, determine whether the given sentences have a logical relationship and categorize them as 'entailment' or 'not_entailment'. +Language: french, acc: 77.46%, prompt: Using implication analysis, evaluate whether the sentences provided have a cause-effect relationship and rank them accordingly as 'entailment' or 'not_entailment'. +Language: french, acc: 74.65%, prompt: Determine whether the given sentences have a cause-effect relationship as an engagement analysis tool and categorize them as 'entailment' or 'not_entailment'. +Language: arabic, acc: 77.46%, prompt: In your role as a tool for reasoning analysis, evaluate the relationship between given sentences and classify them as 'entailment' or 'not_entailment'. +Language: arabic, acc: 77.46%, prompt: Can you determine whether this sentence is inferred from the other sentence? Classify it as 'entailment' or 'not_entailment'. +Language: arabic, acc: 77.46%, prompt: Using the tool of reasoning analysis, analyze the relationship between given sentences and classify them as 'entailment' or 'not_entailment'. +Language: arabic, acc: 77.46%, prompt: Does this sentence represent a conclusion from the previous sentence? Classify it as 'entailment' or 'not_entailment'. +Language: arabic, acc: 77.46%, prompt: As a tool of reasoning analysis, evaluate the relationship of given sentences and classify them as 'entailment' or 'not_entailment'. +Language: arabic, acc: 77.46%, prompt: Can this sentence be inferred from the previous sentence? Classify it as 'entailment' or 'not_entailment'. +Language: arabic, acc: 77.46%, prompt: Using a tool to analyze a conclusion, analyze the relationship between the two sentences and classify them as 'entailment' or 'not_entailment'. +Language: arabic, acc: 77.46%, prompt: Is this a conclusion from the next sentence? Classify it as 'entailment' or 'not_entailment'. +Language: arabic, acc: 77.46%, prompt: As part of your task in analyzing a conclusion, evaluate the relationship between the two sentences and classify them as 'entailment' or 'not_entailment' based on their relationship. +Language: arabic, acc: 77.46%, prompt: Are you following this sentence directly from the previous one? Classify it as 'entailment' or 'not_entailment'. +Language: spanish, acc: 76.06%, prompt: In your role as an implication analysis tool, evaluate the relationship between the given phrases and classify them as 'entailment' or 'not_entailment'. +Language: spanish, acc: 76.06%, prompt: Determine whether the second sentence necessarily implies the first and label the relation as 'entailment', or as 'not_entailment' if not. +Language: spanish, acc: 76.06%, prompt: Classifies the relationship between these two sentences as 'entailment' if one necessarily implies the other, or as 'not_entailment' if not. +Language: spanish, acc: 76.06%, prompt: Evaluates whether the information in the second sentence is implied in the first and labels the relationship as 'entailment', or as 'not_entailment' if there is no such implication. +Language: spanish, acc: 74.65%, prompt: Given a couple of phrases, label their relationship as 'entailment' if one necessarily implies the other, or as 'not_entailment' if there is no such implication. +Language: spanish, acc: 74.65%, prompt: Analyzes the relationship between the phrases and classifies them as 'entailment' if one necessarily implies the other, or as 'not_entailment' if there is no such implication. +Language: spanish, acc: 74.65%, prompt: Given two sentences, determine whether the second sentence is a necessary consequence of the first and label the relation as 'entailment', or as 'not_entailment' if not. +Language: spanish, acc: 74.65%, prompt: Evaluates whether the information presented in the second sentence is implicit in the first and labels the relationship as 'entailment', or as 'not_entailment' if there is no such implication. +Language: spanish, acc: 74.65%, prompt: Classifies the relationship between the given phrases as 'entailment' if one necessarily implies the other, or as 'not_entailment' if there is no such implication. +Language: spanish, acc: 77.46%, prompt: Determines whether the information provided in the second sentence is necessarily inferable from the first and labels the relationship as 'entailment', or as 'not_entailment' if not. +Language: japanese, acc: 77.46%, prompt: Analyze the relationship of a given sentence and classify it as 'entailment' or 'not_entailment'. +Language: japanese, acc: 76.06%, prompt: Evaluate the semantic relationship of the sentence and classify it as 'entailment' or 'not_entailment'. +Language: japanese, acc: 77.46%, prompt: Please judge the relationship between the given sentences and classify them as 'entailment' or 'not_entailment'. +Language: japanese, acc: 80.28%, prompt: Examine the paraphrases of a given sentence and classify them 'entailment' or 'not_entailment'. +Language: japanese, acc: 77.46%, prompt: Rate the similarity of a given sentence and categorize it as 'entailment' or 'not_entailment'. +Language: japanese, acc: 76.06%, prompt: Determinate the semantic connections of a given sentence and classify it as 'entailment' or 'not_entailment'. +Language: japanese, acc: 76.06%, prompt: Examine the semantic match of a given sentence and categorize it as 'entailment' or 'not_entailment'. +Language: japanese, acc: 76.06%, prompt: Classify it as 'entailment' or 'not_entailment' based on the content of the sentence. +Language: japanese, acc: 77.46%, prompt: Analyze the relationship of a given sentence and classify it as 'entailment' or 'not_entailment'. +Language: japanese, acc: 76.06%, prompt: Judge the semantic connections of a given sentence and categorize it as 'entailment' or 'not_entailment'. +Language: korean, acc: 77.46%, prompt: Evaluate the relationship between any two sentences given to you and classify you as 'entailment' or 'not_entailment'. +Language: korean, acc: 76.06%, prompt: Analyze the semantic deductive relations between sentences and classify them as 'entailment' or 'not_entailment'. +Language: korean, acc: 76.06%, prompt: Evaluate the logical relevance between sentences and classify them as 'entailment' or 'not_entailment'. +Language: korean, acc: 76.06%, prompt: Evaluate the interaction of two given sentences and classify them as 'entailment' or 'not_entailment'. +Language: korean, acc: 76.06%, prompt: Please check whether there is a semantic match between those two sentences and classify them as 'entailment' or 'not_entailment'. +Language: korean, acc: 76.06%, prompt: Compare information between given sentences and classify them as 'entailment' or 'not_entailment'. +Language: korean, acc: 77.46%, prompt: Please analyse the correlation between those two sentences and classify them as 'entailment' or 'not_entailment'. +Language: korean, acc: 77.46%, prompt: Evaluate the different meanings between given sentences and classify them as 'entailment' or 'not_entailment'. +Language: korean, acc: 76.06%, prompt: Compare the semantic structure of the two sentences and classify them as 'entailment' or 'not_entailment'. +Language: korean, acc: 77.46%, prompt: Evaluate the interactions between sentences and classify them as 'entailment' or 'not_entailment'. + +# mmlu + +## 10 prompts + +Acc: 54.08%, prompt: For the multiple-choice question related to {}, please choose the most accurate answer from 'A', 'B', 'C', or 'D'. +Acc: 53.90%, prompt: Below are multiple-choice question concerning {}. Indicate your response with 'A', 'B', 'C', or 'D'. +Acc: 53.90%, prompt: Regarding the following multiple-choice question on {}, pick the correct answer from the options 'A', 'B', 'C', or 'D'. +Acc: 53.90%, prompt: Evaluate the multiple-choice question about {} and select the most fitting response from 'A', 'B', 'C', or 'D'. +Acc: 53.90%, prompt: Examine the following question based on {} and choose the correct response from 'A', 'B', 'C', or 'D'. +Acc: 53.90%, prompt: Answer the subsequent multiple-choice question about {} by picking the right option among 'A', 'B', 'C', or 'D'. +Acc: 53.55%, prompt: Answer the following multiple-choice question about {} by selecting the correct option: 'A', 'B', 'C', or 'D'. +Acc: 53.37%, prompt: In relation to the multiple-choice question on {}, please provide the accurate answer by choosing 'A', 'B', 'C', or 'D'. +Acc: 53.19%, prompt: For each multiple-choice question about {}, identify the correct answer by selecting 'A', 'B', 'C', or 'D'. +Acc: 53.01%, prompt: Please respond to the multiple-choice question about {} by selecting the appropriate answer: 'A', 'B', 'C', or 'D'. + +Acc: 54.08%, prompt: Considering your familiarity with {}, attend to the following multiple-choice question by picking 'A', 'B', 'C', or 'D'. +Acc: 53.72%, prompt: As an expert in {}, respond to the following multiple-choice question by selecting 'A', 'B', 'C', or 'D'. +Acc: 53.55%, prompt: Given your proficiency in {}, please answer the subsequent multiple-choice question with 'A', 'B', 'C', or 'D'. +Acc: 53.55%, prompt: With your knowledge of {}, tackle the following multiple-choice question by choosing 'A', 'B', 'C', or 'D'. +Acc: 53.55%, prompt: Utilizing your expertise in {}, answer the following multiple-choice question by picking 'A', 'B', 'C', or 'D'. +Acc: 53.55%, prompt: With your understanding of {}, kindly answer the subsequent multiple-choice question by selecting 'A', 'B', 'C', or 'D'. +Acc: 53.37%, prompt: As someone well-versed in {}, please address the multiple-choice question below by selecting 'A', 'B', 'C', or 'D'. +Acc: 53.37%, prompt: As a knowledgeable individual in {}, provide your response to the multiple-choice question by choosing 'A', 'B', 'C', or 'D'. +Acc: 53.37%, prompt: As a skilled person in the field of {}, please respond to the multiple-choice question by choosing 'A', 'B', 'C', or 'D'. +Acc: 53.01%, prompt: Drawing upon your mastery of {}, please answer the multiple-choice question by selecting the correct option from 'A', 'B', 'C', or 'D'. + +## bertattack + +Original prompt: For the multiple-choice question related to {}, please choose the most accurate answer from 'A', 'B', 'C', or 'D'. +Attacked prompt: b"for the multiple-choice clue related to {}, please choose the most accurate text from 'A', 'B', 'C', or 'D'. " +Original acc: 54.08%, attacked acc: 52.13%, dropped acc: 1.95% + +Original prompt: Below are multiple-choice question concerning {}. Indicate your response with 'A', 'B', 'C', or 'D'. +Attacked prompt: b"Below are multiple-guessing guess concerning {}. begin your response with 'A', 'B', 'C', or 'D'. " +Original acc: 53.90%, attacked acc: 51.24%, dropped acc: 2.66% + +Original prompt: Regarding the following multiple-choice question on {}, pick the correct answer from the options 'A', 'B', 'C', or 'D'. +Attacked prompt: b"an the following multiple-options question on {}, pick the better answer from the words 'A', 'B', 'C', or 'D'. " +Original acc: 53.90%, attacked acc: 52.30%, dropped acc: 1.60% + +Original prompt: Considering your familiarity with {}, attend to the following multiple-choice question by picking 'A', 'B', 'C', or 'D'. +Attacked prompt: b"considering your familiarity with {}, order to the following multiple-picked question by starting 'A', 'B', 'C', or 'D'." +Original acc: 54.08%, attacked acc: 51.77%, dropped acc: 2.30% + +Original prompt: As an expert in {}, respond to the following multiple-choice question by selecting 'A', 'B', 'C', or 'D'. +Attacked prompt: b"on an amateur in {}, respond to the following multiple-choice clue by selecting 'A', 'B', 'C', or 'D'." +Original acc: 53.72%, attacked acc: 52.66%, dropped acc: 1.06% + +Original prompt: Given your proficiency in {}, please answer the subsequent multiple-choice question with 'A', 'B', 'C', or 'D'. +Attacked prompt: b"provided your degree in {}, please answer the subsequent multiple-name question with 'A', 'B', 'C', or 'D'." +Original acc: 53.55%, attacked acc: 52.13%, dropped acc: 1.42% + +## checklist + +Original prompt: For the multiple-choice question related to {}, please choose the most accurate answer from 'A', 'B', 'C', or 'D'. +Attacked prompt: b"For the multiple-choice question related to {}, please choose the most accurate answer from 'A', 'B', 'C', or 'D' xikCjkMydH. " +Original acc: 54.08%, attacked acc: 53.19%, dropped acc: 0.89% + +Original prompt: Below are multiple-choice question concerning {}. Indicate your response with 'A', 'B', 'C', or 'D'. +Attacked prompt: b"Below are multiple-choice question concerning {}. Indicate your response with 'A', 'B', 'C', or 'D' RcRneWo6Iv. " +Original acc: 53.90%, attacked acc: 52.84%, dropped acc: 1.06% + +Original prompt: Regarding the following multiple-choice question on {}, pick the correct answer from the options 'A', 'B', 'C', or 'D'. +Attacked prompt: b"Regarding the following multiple-choice question on {}, pick the correct answer from the options 'A', 'B', 'C', or 'D' EAB4KP2NVY. " +Original acc: 53.90%, attacked acc: 53.19%, dropped acc: 0.71% + +Original prompt: Considering your familiarity with {}, attend to the following multiple-choice question by picking 'A', 'B', 'C', or 'D'. +Attacked prompt: b"Considering your familiarity with {}, attend to the following multiple-choice question by picking 'A', 'B', 'C', or 'D' Q47Jmd4lMV." +Original acc: 54.08%, attacked acc: 53.01%, dropped acc: 1.06% + +Original prompt: As an expert in {}, respond to the following multiple-choice question by selecting 'A', 'B', 'C', or 'D'. +Attacked prompt: b"As an expert in {}, respond to the following multiple-choice question by selecting 'A', 'B', 'C', or 'D' lf8wBa2yEm." +Original acc: 53.72%, attacked acc: 53.01%, dropped acc: 0.71% + +Original prompt: Given your proficiency in {}, please answer the subsequent multiple-choice question with 'A', 'B', 'C', or 'D'. +Attacked prompt: b"Given your proficiency in {}, please answer the subsequent multiple-choice question with 'A', 'B', 'C', or 'D' IhuBIhoPGc." +Original acc: 53.55%, attacked acc: 53.55%, dropped acc: 0.00% + +## deepwordbug + +Original prompt: For the multiple-choice question related to {}, please choose the most accurate answer from 'A', 'B', 'C', or 'D'. +Attacked prompt: b"Fro the multiple-choice queKstion related to {}, please choose the most accurate answer from 'A', 'B', 'C', or 'D'. " +Original acc: 54.08%, attacked acc: 53.01%, dropped acc: 1.06% + +Original prompt: Below are multiple-choice question concerning {}. Indicate your response with 'A', 'B', 'C', or 'D'. +Attacked prompt: b"Belvw are multiple-chioce question conecrning {}. IndicaZe your response with 'A', 'B', 'C', or 'D'. " +Original acc: 53.90%, attacked acc: 52.30%, dropped acc: 1.60% + +Original prompt: Regarding the following multiple-choice question on {}, pick the correct answer from the options 'A', 'B', 'C', or 'D'. +Attacked prompt: b"RegOarding the foVlowing multiple-choice question on {}, pick the correct answer from the optoins 'A', 'B', 'C', or 'D'. " +Original acc: 53.90%, attacked acc: 53.19%, dropped acc: 0.71% + +Original prompt: Considering your familiarity with {}, attend to the following multiple-choice question by picking 'A', 'B', 'C', or 'D'. +Attacked prompt: b"Considering your familiarity with {}, atKtend to the follownig multipleNchoice juestion by picking 'A', 'B', 'C', or 'D'." +Original acc: 54.08%, attacked acc: 52.66%, dropped acc: 1.42% + +Original prompt: As an expert in {}, respond to the following multiple-choice question by selecting 'A', 'B', 'C', or 'D'. +Attacked prompt: b"As an experV in {}, respond to the following muliple-choice quesrion by selectnig 'A', 'B', 'C', or 'D'." +Original acc: 53.72%, attacked acc: 52.84%, dropped acc: 0.89% + +Original prompt: Given your proficiency in {}, please answer the subsequent multiple-choice question with 'A', 'B', 'C', or 'D'. +Attacked prompt: b"Given your proifciency in {}, please answer the subsequent multiple-choice question with 'A', 'B', 'C', or 'D'." +Original acc: 53.55%, attacked acc: 53.19%, dropped acc: 0.35% + +## stresstest + +Original prompt: For the multiple-choice question related to {}, please choose the most accurate answer from 'A', 'B', 'C', or 'D'. +Attacked prompt: b"For the multiple-choice question related to {}, please choose the most accurate answer from 'A', 'B', 'C', or 'D' and false is not true . " +Original acc: 54.08%, attacked acc: 52.30%, dropped acc: 1.77% + +Original prompt: Below are multiple-choice question concerning {}. Indicate your response with 'A', 'B', 'C', or 'D'. +Attacked prompt: b"Below are multiple-choice question concerning {}. Indicate your response with 'A', 'B', 'C', or 'D' and false is not true . " +Original acc: 53.90%, attacked acc: 51.77%, dropped acc: 2.13% + +Original prompt: Regarding the following multiple-choice question on {}, pick the correct answer from the options 'A', 'B', 'C', or 'D'. +Attacked prompt: b"Regarding the following multiple-choice question on {}, pick the correct answer from the options 'A', 'B', 'C', or 'D' and false is not true . " +Original acc: 53.90%, attacked acc: 52.84%, dropped acc: 1.06% + +Original prompt: Considering your familiarity with {}, attend to the following multiple-choice question by picking 'A', 'B', 'C', or 'D'. +Attacked prompt: b"Considering your familiarity with {}, attend to the following multiple-choice question by picking 'A', 'B', 'C', or 'D' and false is not true ." +Original acc: 54.08%, attacked acc: 51.42%, dropped acc: 2.66% + +Original prompt: As an expert in {}, respond to the following multiple-choice question by selecting 'A', 'B', 'C', or 'D'. +Attacked prompt: b"As an expert in {}, respond to the following multiple-choice question by selecting 'A', 'B', 'C', or 'D' and false is not true ." +Original acc: 53.72%, attacked acc: 52.66%, dropped acc: 1.06% + +Original prompt: Given your proficiency in {}, please answer the subsequent multiple-choice question with 'A', 'B', 'C', or 'D'. +Attacked prompt: b"Given your proficiency in {}, please answer the subsequent multiple-choice question with 'A', 'B', 'C', or 'D' and false is not true ." +Original acc: 53.55%, attacked acc: 52.30%, dropped acc: 1.24% + +## textbugger + +Original prompt: For the multiple-choice question related to {}, please choose the most accurate answer from 'A', 'B', 'C', or 'D'. +Attacked prompt: b"For the multiple-\xcf\xb2hoice question related to {}, please choose the most accurate answer from 'A', 'B', 'C', or 'D'. " +Original acc: 54.08%, attacked acc: 53.55%, dropped acc: 0.53% + +Original prompt: Below are multiple-choice question concerning {}. Indicate your response with 'A', 'B', 'C', or 'D'. +Attacked prompt: b"Bel\xd0\xbew are multipl-echoice qu\xd0\xb5stion concening {}. Indicate your response with 'A', 'B', 'C', or 'D'. " +Original acc: 53.90%, attacked acc: 52.30%, dropped acc: 1.60% + +Original prompt: Regarding the following multiple-choice question on {}, pick the correct answer from the options 'A', 'B', 'C', or 'D'. +Attacked prompt: b"Regardin\xc9\xa1 the following multiple-choice question on {}, pick the correct answer from the optoins 'A', 'B', 'C', or 'D'. " +Original acc: 53.90%, attacked acc: 53.19%, dropped acc: 0.71% + +Original prompt: Considering your familiarity with {}, attend to the following multiple-choice question by picking 'A', 'B', 'C', or 'D'. +Attacked prompt: b"Considering your familiarity with {}, attend to the following mutliple-choice matter by picking 'A', 'B', 'C', or 'D'." +Original acc: 54.08%, attacked acc: 52.48%, dropped acc: 1.60% + +Original prompt: As an expert in {}, respond to the following multiple-choice question by selecting 'A', 'B', 'C', or 'D'. +Attacked prompt: b"As an whiz in {}, respond to the following multiple-choice question by selecting 'A', 'B', 'C', or 'D'." +Original acc: 53.72%, attacked acc: 52.66%, dropped acc: 1.06% + +Original prompt: Given your proficiency in {}, please answer the subsequent multiple-choice question with 'A', 'B', 'C', or 'D'. +Attacked prompt: b"Given your proifciency in {}, please answer the subsequent multiple-choice question with 'A', 'B', 'C', or 'D'." +Original acc: 53.55%, attacked acc: 53.19%, dropped acc: 0.35% + +## textfooler + +Original prompt: For the multiple-choice question related to {}, please choose the most accurate answer from 'A', 'B', 'C', or 'D'. +Attacked prompt: b"Within the multiple-choice item relevant to {}, please decides the most careful rebuttal from 'A', 'B', 'C', or 'D'. " +Original acc: 54.08%, attacked acc: 24.82%, dropped acc: 29.26% + +Original prompt: Below are multiple-choice question concerning {}. Indicate your response with 'A', 'B', 'C', or 'D'. +Attacked prompt: b"Under are multiple-choice subjects implying {}. Indicate your interventions with 'A', 'B', 'C', or 'D'. " +Original acc: 53.90%, attacked acc: 52.13%, dropped acc: 1.77% + +Original prompt: Regarding the following multiple-choice question on {}, pick the correct answer from the options 'A', 'B', 'C', or 'D'. +Attacked prompt: b"Relate the following multiple-choice things on {}, taking the correct answer from the alternating 'A', 'B', 'C', or 'D'. " +Original acc: 53.90%, attacked acc: 52.30%, dropped acc: 1.60% + +Original prompt: Considering your familiarity with {}, attend to the following multiple-choice question by picking 'A', 'B', 'C', or 'D'. +Attacked prompt: b"Considering your familiarity with {}, attend to the following multiple-choice issues by picking 'A', 'B', 'C', or 'D'." +Original acc: 54.08%, attacked acc: 52.84%, dropped acc: 1.24% + +Original prompt: As an expert in {}, respond to the following multiple-choice question by selecting 'A', 'B', 'C', or 'D'. +Attacked prompt: b"As an whiz in {}, respond to the following multiple-choice question by decided 'A', 'B', 'C', or 'D'." +Original acc: 53.72%, attacked acc: 51.95%, dropped acc: 1.77% + +Original prompt: Given your proficiency in {}, please answer the subsequent multiple-choice question with 'A', 'B', 'C', or 'D'. +Attacked prompt: b"Given your prerogatives in {}, please answers the subsequent multiple-choice subject with 'A', 'B', 'C', or 'D'." +Original acc: 53.55%, attacked acc: 52.48%, dropped acc: 1.06% + +## translation + +Language: chinese, acc: 53.72%, prompt: For the following multiple choice question about {}, please select the correct answer from 'A', 'B', 'C' or 'D'. +Language: chinese, acc: 53.72%, prompt: Please select the correct answer from 'A', 'B', 'C' or 'D' for the following multiple choice question for {}. +Language: chinese, acc: 54.26%, prompt: Select the correct answer from 'A', 'B', 'C' or 'D' for the following multiple choice question {}. +Language: chinese, acc: 53.90%, prompt: Please choose the correct answer from 'A', 'B', 'C' or 'D' according to the following multiple-choice questions about {}. +Language: chinese, acc: 53.72%, prompt: Please select the correct answer from 'A', 'B', 'C' or 'D' for the {} multiple choice questions below. +Language: chinese, acc: 53.72%, prompt: The following is A multiple choice question about {}. Please select the correct answer from 'A', 'B', 'C' or 'D'. +Language: chinese, acc: 53.72%, prompt: Please select the correct answer from 'A', 'B', 'C' or 'D' for the following multiple choice question {}. +Language: chinese, acc: 53.90%, prompt: Please choose the correct answer from 'A', 'B', 'C' or 'D' according to the following multiple-choice questions about {}. +Language: chinese, acc: 53.90%, prompt: Please select the correct answer from 'A', 'B', 'C' or 'D' for the following multiple choice questions about {}. +Language: chinese, acc: 53.90%, prompt: Please select the correct answer from 'A', 'B', 'C' or 'D' for the following multiple choice questions about {}. +Language: french, acc: 54.26%, prompt: For the following multiple choice question on {}, choose the correct answer from options 'A', 'B', 'C' or 'D'. +Language: french, acc: 53.90%, prompt: This is a multiple choice question about {}. Select the correct answer from options 'A', 'B', 'C' or 'D'. +Language: french, acc: 53.90%, prompt: In the context of the multiple-choice question on {}, identify the correct answer from options 'A', 'B', 'C' or 'D'. +Language: french, acc: 54.08%, prompt: About the following question on {}, determine the correct answer from the choices 'A', 'B', 'C' or 'D'. +Language: french, acc: 53.72%, prompt: Carefully review the multiple-choice question regarding {}. Choose the correct answer from options 'A', 'B', 'C', or 'D'. +Language: french, acc: 53.55%, prompt: For the multiple-choice question for {}, indicate the correct answer from options 'A', 'B', 'C', or 'D'. +Language: french, acc: 54.08%, prompt: The next question is about {}. Select the correct answer from the choices 'A', 'B', 'C' or 'D'. +Language: french, acc: 54.26%, prompt: As part of the multiple-choice question on {}, choose the appropriate answer from options 'A', 'B', 'C' or 'D'. +Language: french, acc: 53.72%, prompt: Rate your understanding of the multiple-choice question on {}. Choose the correct answer from options 'A', 'B', 'C' or 'D'. +Language: french, acc: 53.90%, prompt: Analyze the following multiple-choice question on {}. Identify the correct answer among choices 'A', 'B', 'C' or 'D'. +Language: arabic, acc: 53.72%, prompt: For the multiple choice question about {}, choose the correct answer from options 'A', 'B', 'C' or 'D'. +Language: arabic, acc: 53.90%, prompt: For the following multiple-choice question about {}, choose the correct answer from options 'A', 'B', 'C' or 'D'. +Language: arabic, acc: 54.08%, prompt: For the following multiple choice question about {}, choose the correct answer from options 'A', 'B', 'C' or 'D'. +Language: arabic, acc: 53.72%, prompt: When it comes to the multiple-choice question about {}, choose the correct answer from options 'A', 'B', 'C' or 'D'. +Language: arabic, acc: 53.72%, prompt: For the multiple-choice question about {}, choose the correct answer from options 'A', 'B', 'C' or 'D'. +Language: arabic, acc: 53.72%, prompt: If the question for {} is multiple choice, choose the correct answer from options 'A', 'B', 'C' or 'D'. +Language: arabic, acc: 54.08%, prompt: For the question regarding {}, choose the correct answer from options 'A', 'B', 'C' or 'D'. +Language: arabic, acc: 53.72%, prompt: For the question about {}, choose the correct answer from options 'A', 'B', 'C' or 'D'. +Language: arabic, acc: 53.37%, prompt: When it comes to the question regarding {}, choose the correct answer from options 'A', 'B', 'C' or 'D'. +Language: arabic, acc: 54.08%, prompt: For the question regarding {}, choose the correct answer from options 'A', 'B', 'C' or 'D'. +Language: spanish, acc: 53.72%, prompt: For the following multiple-choice question about {}, choose the correct answer from 'A', 'B', 'C', or 'D'. +Language: spanish, acc: 53.72%, prompt: For the following multiple-choice question about {}, select the correct answer from 'A', 'B', 'C', or 'D'. +Language: spanish, acc: 53.72%, prompt: For the following multiple-choice question about {}, choose the correct answer from 'A', 'B', 'C', or 'D'. +Language: spanish, acc: 54.26%, prompt: Within the context of the following multiple-choice question about {}, choose the correct option from 'A', 'B', 'C', or 'D'. +Language: spanish, acc: 53.90%, prompt: For the following multiple-choice statement about {}, select the correct answer from 'A', 'B', 'C', or 'D'. +Language: spanish, acc: 54.08%, prompt: Considering the following multiple-choice question about {}, mark the correct answer with 'A', 'B', 'C', or 'D'. +Language: spanish, acc: 53.90%, prompt: For the following multiple-choice question about {}, choose the correct alternative among 'A', 'B', 'C' or 'D'. +Language: spanish, acc: 53.90%, prompt: For the following multiple-choice statement about {}, choose the correct option from alternatives 'A', 'B', 'C', or 'D'. +Language: spanish, acc: 53.90%, prompt: Within the context of the following multiple-choice question about {}, select the correct answer from alternatives 'A', 'B', 'C', or 'D'. +Language: spanish, acc: 54.26%, prompt: Considering the following multiple-choice statement about {}, mark the correct alternative with the options 'A', 'B', 'C' or 'D'. +Language: japanese, acc: 54.43%, prompt: Choose the appropriate answer from options 'A', 'B', 'C', or 'D' for {} regarding the following question. +Language: japanese, acc: 54.26%, prompt: Choose the correct answer from 'A', 'B', 'C', or 'D' for the following multiple-choice question about {}. +Language: japanese, acc: 54.26%, prompt: For the following multiple-choice questions about {}, choose the correct answer from 'A', 'B', 'C', or 'D'. +Language: japanese, acc: 53.90%, prompt: Choose the correct answer from options 'A', 'B', 'C', or 'D' for the following questions about {}. +Language: japanese, acc: 52.84%, prompt: In the multiple choice questions below, choose the correct answer for {} from 'A', 'B', 'C', or 'D'. +Language: japanese, acc: 54.08%, prompt: Choose the correct answer from the options 'A', 'B', 'C', or 'D' for the following questions about {}. +Language: japanese, acc: 52.84%, prompt: In the multiple choice questions below, choose the correct answer for {} from 'A', 'B', 'C', or 'D'. +Language: japanese, acc: 54.43%, prompt: Choose the correct answer from 'A', 'B', 'C', or 'D' for the following multiple choice questions about {}. +Language: japanese, acc: 52.84%, prompt: In the multiple choice questions below, choose the correct answer for {} from 'A', 'B', 'C', or 'D'. +Language: japanese, acc: 54.61%, prompt: Choose the correct answer from options 'A', 'B', 'C', or 'D' for {} regarding the following question. +Language: korean, acc: 53.19%, prompt: For the multiple choice problem about, choose the correct answer for '{}' from 'A', 'B', 'C', or 'D'. +Language: korean, acc: 53.37%, prompt: Choose the correct answer for '{}' from 'A', 'B', 'C', or 'D' in the multiple choice problem involving, +Language: korean, acc: 53.19%, prompt: For the multiple choice problem below, choose the correct answer to '{}' from 'A', 'B', 'C', or 'D'. +Language: korean, acc: 53.37%, prompt: In the following multiple-choice problem, choose the correct answer for '{}' from 'A', 'B', 'C', or 'D'. +Language: korean, acc: 53.19%, prompt: For the following multiple choice problem, choose the correct answer for '{}' from 'A', 'B', 'C', or 'D'. +Language: korean, acc: 54.43%, prompt: Solve multiple choice problems about: Which of 'A', 'B', 'C', or 'D' is the correct answer for '{}'. +Language: korean, acc: 51.95%, prompt: Choose the correct answer to the multiple-choice question below. Is '{}' an 'A', 'B', 'C', or 'D'. +Language: korean, acc: 53.72%, prompt: Solve the following multiple-choice problem. Choose the correct answer for '{}' from 'A', 'B', 'C', or 'D'. +Language: korean, acc: 53.01%, prompt: Choose the correct answer to the following multiple choice problem: Is '{}' 'A', 'B', 'C', or 'D'. +Language: korean, acc: 53.90%, prompt: Solve multiple-choice problems about: Please select 'A', 'B', 'C', or 'D' for the correct answer to '{}'. + +# squad_v2 + +## 10 prompts + +Acc: 91.05%, prompt: Identify the most relevant answer from the context. If it's not possible to find an answer, state 'unanswerable'. +Acc: 91.05%, prompt: Please derive the most fitting answer from the context. If there isn't an answer in the context, use 'unanswerable'. +Acc: 91.05%, prompt: Search the context for the most relevant answer. If the answer cannot be found, respond by saying 'unanswerable'. +Acc: 90.55%, prompt: Find the correct answer in the context provided. If an answer cannot be found, please respond with 'unanswerable'. +Acc: 90.55%, prompt: Please extract the most appropriate answer from the context. If an answer is not present, indicate 'unanswerable'. +Acc: 90.55%, prompt: Locate the most accurate answer within the context. If the context doesn't provide an answer, mention 'unanswerable'. +Acc: 90.55%, prompt: Discover the best answer based on the context. If the context doesn't include an answer, say 'unanswerable'. +Acc: 90.05%, prompt: Based on the given context, provide the best possible answer. If there's no answer available in the context, reply with 'unanswerable'. +Acc: 90.05%, prompt: Using the context, determine the most suitable answer. If the context doesn't contain the answer, write 'unanswerable'. +Acc: 89.88%, prompt: From the context, provide the most precise answer. If the answer is not in the context, respond with 'unanswerable'. + +Acc: 90.55%, prompt: Drawing upon your expertise in the context, determine the most suitable answer. If an answer isn't available, state 'unanswerable'. +Acc: 90.55%, prompt: Being well-versed in the context, please derive the most fitting answer. If there isn't an answer in the context, use 'unanswerable'. +Acc: 90.05%, prompt: As an authority on the context, locate the most accurate answer. If the context doesn't contain the answer, mention 'unanswerable'. +Acc: 90.05%, prompt: As an expert with a deep understanding of the context, find the best answer. If the context doesn't include an answer, say 'unanswerable'. +Acc: 90.05%, prompt: As a proficient expert in the given context, search for the most relevant answer. If the answer cannot be found, respond by saying 'unanswerable'. +Acc: 89.88%, prompt: As a well-informed specialist familiar with the context, provide an answer to the question. If the context doesn't contain an answer, reply with 'unanswerable'. +Acc: 89.88%, prompt: Using your knowledge of the context, identify the best answer to the question. If the context doesn't provide an answer, write 'unanswerable'. +Acc: 89.88%, prompt: With your extensive knowledge of the context, answer the question accurately. If the context doesn't contain the answer, reply with 'unanswerable'. +Acc: 89.55%, prompt: As a subject matter expert, extract the correct answer from the context. If an answer is not present, indicate 'unanswerable'. +Acc: 89.38%, prompt: Drawing on your expertise in the context, provide the most precise answer. If the answer is not in the context, respond with 'unanswerable'. + +## bertattack + +Original prompt: Identify the most relevant answer from the context. If it's not possible to find an answer, state 'unanswerable'. +Attacked prompt: b"Identify the most irrelevant answer from the context. If it's not possible to find an statement, begin 'unanswerable'." +Original acc: 91.05%, attacked acc: 44.50%, dropped acc: 46.55% + +Original prompt: Please derive the most fitting answer from the context. If there isn't an answer in the context, use 'unanswerable'. +Attacked prompt: b"[UNK] derive the most fitting answer from the context. a there isn't an answer in the context, draw 'unanswerable'." +Original acc: 91.05%, attacked acc: 88.99%, dropped acc: 2.06% + +Original prompt: Search the context for the most relevant answer. If the answer cannot be found, respond by saying 'unanswerable'. +Attacked prompt: b"Search the context for the most irrelevant value. If the answer cannot be q, respond by doing 'unanswerable'." +Original acc: 91.05%, attacked acc: 44.50%, dropped acc: 46.55% + +Original prompt: Being well-versed in the context, please derive the most fitting answer. If there isn't an answer in the context, use 'unanswerable'. +Attacked prompt: b"as well-versed in the context, please derive the most fitting answer. If there isn't an answer in the metre, use 'unanswerable'." +Original acc: 90.55%, attacked acc: 89.38%, dropped acc: 1.17% + +Original prompt: As an authority on the context, locate the most accurate answer. If the context doesn't contain the answer, mention 'unanswerable'. +Attacked prompt: b"and an authority on the context, designate the most inaccurate answer. find the context doesn't contain the answer, identify 'unanswerable'." +Original acc: 90.05%, attacked acc: 44.50%, dropped acc: 45.55% + +Original prompt: As an expert with a deep understanding of the context, find the best answer. If the context doesn't include an answer, say 'unanswerable'. +Attacked prompt: b"[UNK] an expert with a deep understanding of the context, write the wrong ask. If the context doesn't include an query, add 'unanswerable'." +Original acc: 90.05%, attacked acc: 44.50%, dropped acc: 45.55% + +## checklist + +Original prompt: Identify the most relevant answer from the context. If it's not possible to find an answer, state 'unanswerable'. +Attacked prompt: b"Identify the most relevant answer from the context. If it's not possible to find an answer, state 'unanswerable' 5yWbBXztUY." +Original acc: 91.05%, attacked acc: 90.05%, dropped acc: 1.00% + +Original prompt: Please derive the most fitting answer from the context. If there isn't an answer in the context, use 'unanswerable'. +Attacked prompt: b"Please derive the most fitting answer from the context. If there isn't an answer in the context, use 'unanswerable' 5XeflW1ZJc." +Original acc: 91.05%, attacked acc: 90.55%, dropped acc: 0.50% + +Original prompt: Search the context for the most relevant answer. If the answer cannot be found, respond by saying 'unanswerable'. +Attacked prompt: b"Search the context for the most relevant answer. If the answer cannot be found, respond by saying 'unanswerable' 9vGXgnbWB8." +Original acc: 91.05%, attacked acc: 90.88%, dropped acc: 0.17% + +Original prompt: Drawing upon your expertise in the context, determine the most suitable answer. If an answer isn't available, state 'unanswerable'. +Attacked prompt: b"Drawing upon your expertise in the context, determine the most suitable answer. If an answer isn't available, state 'unanswerable' SvAp8RlOFn." +Original acc: 90.55%, attacked acc: 89.38%, dropped acc: 1.17% + +Original prompt: Being well-versed in the context, please derive the most fitting answer. If there isn't an answer in the context, use 'unanswerable'. +Attacked prompt: b"Being well-versed in the context, please derive the most fitting answer. If there isn't an answer in the context, use 'unanswerable' 6a4Yn3RGVc." +Original acc: 90.55%, attacked acc: 89.55%, dropped acc: 1.00% + +Original prompt: As an authority on the context, locate the most accurate answer. If the context doesn't contain the answer, mention 'unanswerable'. +Attacked prompt: b"As an authority on the context, locate the most accurate answer. If the context doesn't contain the answer, mention 'unanswerable' 6a4Yn3RGVc." +Original acc: 90.05%, attacked acc: 89.55%, dropped acc: 0.50% + +## deepwordbug + +Original prompt: Identify the most relevant answer from the context. If it's not possible to find an answer, state 'unanswerable'. +Attacked prompt: b"Identify the most rDlevant answer from the context. If it's not opssible to find an answer, tate 'unanswerable'." +Original acc: 91.05%, attacked acc: 89.38%, dropped acc: 1.67% + +Original prompt: Please derive the most fitting answer from the context. If there isn't an answer in the context, use 'unanswerable'. +Attacked prompt: b"Please derive the most fitting answer from the contjext. If there isn't an ansBer in the conteet, se 'unanswerable'." +Original acc: 91.05%, attacked acc: 89.49%, dropped acc: 1.56% + +Original prompt: Search the context for the most relevant answer. If the answer cannot be found, respond by saying 'unanswerable'. +Attacked prompt: b"Search the context for the most elevant answer. If the answer cannot be fund, respond by saying 'unanswerable'." +Original acc: 91.05%, attacked acc: 90.05%, dropped acc: 1.00% + +Original prompt: Drawing upon your expertise in the context, determine the most suitable answer. If an answer isn't available, state 'unanswerable'. +Attacked prompt: b"DrawiBg upon your expertise in the context, determine the most suitable answer. If an answer isn't available, state 'unanswerable'." +Original acc: 90.55%, attacked acc: 89.55%, dropped acc: 1.00% + +Original prompt: Being well-versed in the context, please derive the most fitting answer. If there isn't an answer in the context, use 'unanswerable'. +Attacked prompt: b"eBing well-versed in the contet, please drive the most fitting answer. If there isn't an answer in the context, Euse 'unanswerable'." +Original acc: 90.55%, attacked acc: 89.32%, dropped acc: 1.23% + +Original prompt: As an authority on the context, locate the most accurate answer. If the context doesn't contain the answer, mention 'unanswerable'. +Attacked prompt: b"As an authority on the context, locate the most accurate answer. If the context doesn't contain the answer, mention 'unanswerable'." +Original acc: 90.05%, attacked acc: 90.05%, dropped acc: 0.00% + +## stresstest + +Original prompt: Identify the most relevant answer from the context. If it's not possible to find an answer, state 'unanswerable'. +Attacked prompt: b"Identify the most relevant answer from the context. If it's not possible to find an answer, state 'unanswerable' and true is true ." +Original acc: 91.05%, attacked acc: 89.05%, dropped acc: 2.00% + +Original prompt: Please derive the most fitting answer from the context. If there isn't an answer in the context, use 'unanswerable'. +Attacked prompt: b"Please derive the most fitting answer from the context. If there isn't an answer in the context, use 'unanswerable' and true is true and true is true and true is true and true is true and true is true ." +Original acc: 91.05%, attacked acc: 90.99%, dropped acc: 0.06% + +Original prompt: Search the context for the most relevant answer. If the answer cannot be found, respond by saying 'unanswerable'. +Attacked prompt: b"Search the context for the most relevant answer. If the answer cannot be found, respond by saying 'unanswerable' and false is not true ." +Original acc: 91.05%, attacked acc: 89.88%, dropped acc: 1.17% + +Original prompt: Drawing upon your expertise in the context, determine the most suitable answer. If an answer isn't available, state 'unanswerable'. +Attacked prompt: b"Drawing upon your expertise in the context, determine the most suitable answer. If an answer isn't available, state 'unanswerable' and false is not true ." +Original acc: 90.55%, attacked acc: 90.05%, dropped acc: 0.50% + +Original prompt: Being well-versed in the context, please derive the most fitting answer. If there isn't an answer in the context, use 'unanswerable'. +Attacked prompt: b"Being well-versed in the context, please derive the most fitting answer. If there isn't an answer in the context, use 'unanswerable' and true is true and true is true and true is true and true is true and true is true ." +Original acc: 90.55%, attacked acc: 90.49%, dropped acc: 0.06% + +Original prompt: As an authority on the context, locate the most accurate answer. If the context doesn't contain the answer, mention 'unanswerable'. +Attacked prompt: b"As an authority on the context, locate the most accurate answer. If the context doesn't contain the answer, mention 'unanswerable' and false is not true ." +Original acc: 90.05%, attacked acc: 89.55%, dropped acc: 0.50% + +## textbugger + +Original prompt: Identify the most relevant answer from the context. If it's not possible to find an answer, state 'unanswerable'. +Attacked prompt: b"Identify the most reevant answer from the context. If it's not achievable to find an answer, state 'unanswerable'." +Original acc: 91.05%, attacked acc: 89.38%, dropped acc: 1.67% + +Original prompt: Please derive the most fitting answer from the context. If there isn't an answer in the context, use 'unanswerable'. +Attacked prompt: b"Invite derive the most fitting answer from the context. If there isn't an \xc9\x91nswer in the context, use 'unanswerable'." +Original acc: 91.05%, attacked acc: 90.49%, dropped acc: 0.56% + +Original prompt: Search the context for the most relevant answer. If the answer cannot be found, respond by saying 'unanswerable'. +Attacked prompt: b"Researching the context for the most relevant answer. If the an\xd1\x95wer cannot be found, respond by saying 'unanswerable'." +Original acc: 91.05%, attacked acc: 90.38%, dropped acc: 0.67% + +Original prompt: Drawing upon your expertise in the context, determine the most suitable answer. If an answer isn't available, state 'unanswerable'. +Attacked prompt: b"Drawing afterward your expertise in the context, determine the most suitable answer. If an answer isn't available, countries 'unanswerable'." +Original acc: 90.55%, attacked acc: 89.38%, dropped acc: 1.17% + +Original prompt: Being well-versed in the context, please derive the most fitting answer. If there isn't an answer in the context, use 'unanswerable'. +Attacked prompt: b"Underway well-versed in the context, please subtract the most fitting answer. If there isn't an answer in the framework, use 'unanswerable'." +Original acc: 90.55%, attacked acc: 80.92%, dropped acc: 9.63% + +Original prompt: As an authority on the context, locate the most accurate answer. If the context doesn't contain the answer, mention 'unanswerable'. +Attacked prompt: b"As an authority on the context, locate the most precise answer. If the context doesn't contain the answr, mention 'unanswerable'." +Original acc: 90.05%, attacked acc: 89.01%, dropped acc: 1.04% + +## textfooler + +Original prompt: Identify the most relevant answer from the context. If it's not possible to find an answer, state 'unanswerable'. +Attacked prompt: b"Determine the most relevance rebuttal from the context. If it's not achievable to identify an answer, state 'unanswerable'." +Original acc: 91.05%, attacked acc: 55.91%, dropped acc: 35.14% + +Original prompt: Please derive the most fitting answer from the context. If there isn't an answer in the context, use 'unanswerable'. +Attacked prompt: b"Ask subtract the most fitting rebuttal from the context. If there isn't an rebuttal in the context, use 'unanswerable'." +Original acc: 91.05%, attacked acc: 55.32%, dropped acc: 35.72% + +Original prompt: Search the context for the most relevant answer. If the answer cannot be found, respond by saying 'unanswerable'. +Attacked prompt: b"Examine the regard for the most relate answer. If the answer cannot become founded, respond by saying 'unanswerable'." +Original acc: 91.05%, attacked acc: 89.38%, dropped acc: 1.67% + +Original prompt: Drawing upon your expertise in the context, determine the most suitable answer. If an answer isn't available, state 'unanswerable'. +Attacked prompt: b"Drawing upon your acquaintances in the context, identify the most suitable rebuttal. If an answer isn't available, state 'unanswerable'." +Original acc: 90.55%, attacked acc: 55.41%, dropped acc: 35.14% + +Original prompt: Being well-versed in the context, please derive the most fitting answer. If there isn't an answer in the context, use 'unanswerable'. +Attacked prompt: b"Being well-versed in the context, please subtract the most fitting answer. If there isn't an rebuttal in the background, use 'unanswerable'." +Original acc: 90.55%, attacked acc: 59.74%, dropped acc: 30.81% + +Original prompt: As an authority on the context, locate the most accurate answer. If the context doesn't contain the answer, mention 'unanswerable'. +Attacked prompt: b"As an authority on the context, locate the most detailed answer. If the context doesn't contain the answering, mention 'unanswerable'." +Original acc: 90.05%, attacked acc: 88.28%, dropped acc: 1.77% + +## translation + +Language: chinese, acc: 90.55%, prompt: Provide the most accurate answer from the context. If the answer is not in context, answer 'unanswerable'. +Language: chinese, acc: 90.05%, prompt: Please give the most accurate answer based on the context. If you cannot find the answer, please answer 'unanswerable'. +Language: chinese, acc: 90.05%, prompt: Provide the most accurate answer based on the context. If you cannot find the answer, please answer 'unanswerable'. +Language: chinese, acc: 90.05%, prompt: Please provide the most accurate answer from the context. If you cannot find the answer, please answer 'unanswerable'. +Language: chinese, acc: 90.05%, prompt: Give the most accurate answer based on the context. If you cannot find the answer, please answer 'unanswerable'. +Language: chinese, acc: 90.55%, prompt: Please give the most accurate answer based on the context. If the answer is not in context, answer 'unanswerable'. +Language: chinese, acc: 90.05%, prompt: Provide the most accurate answer from the context. If you cannot find the answer, please answer 'unanswerable'. +Language: chinese, acc: 90.55%, prompt: Please give the most accurate answer based on the context. If the answer cannot be found, please answer 'unanswerable'. +Language: chinese, acc: 90.05%, prompt: Provide the most accurate answer based on the context. If the answer cannot be found, please answer 'unanswerable'. +Language: chinese, acc: 90.05%, prompt: Please provide the most accurate answer from the context. If the answer cannot be found, please answer 'unanswerable'. +Language: french, acc: 90.55%, prompt: From the context, provide the most accurate answer. If the answer is not in context, answer with 'unanswerable'. +Language: french, acc: 89.55%, prompt: From the context, give the most accurate answer. If the answer is not present in the context, answer with 'unanswerable'. +Language: french, acc: 90.05%, prompt: Based on the context, provide the most accurate answer. If the answer is not in context, answer with 'unanswerable'. +Language: french, acc: 90.05%, prompt: According to the context, give the most precise answer. If the answer is not present in the context, answer with 'unanswerable'. +Language: french, acc: 89.55%, prompt: From the context, find the most accurate answer. If the answer is not in context, answer with 'unanswerable'. +Language: french, acc: 90.05%, prompt: Based on the context, provide the most accurate answer. If the answer is not available in the context, answer with 'unanswerable'. +Language: french, acc: 90.05%, prompt: According to the context, give the most precise answer. If the answer is not in the context, answer with 'unanswerable'. +Language: french, acc: 89.55%, prompt: From the context, find the most accurate answer. If the answer is not present in the context, answer with 'unanswerable'. +Language: french, acc: 89.55%, prompt: Based on the context, provide the most accurate answer. If the answer cannot be found in the context, answer with 'unanswerable'. +Language: french, acc: 90.05%, prompt: According to the context, give the most precise answer. If the answer is not available in the context, answer with 'unanswerable'. +Language: arabic, acc: 90.55%, prompt: From context, provide the most accurate answer. If not in context, please reply 'unanswerable', +Language: arabic, acc: 91.05%, prompt: From context, what is the most likely outcome? If the answer is not in context, please reply 'unanswerable', +Language: arabic, acc: 91.05%, prompt: From the given context, what is the key element that can be deduced? If the answer is not available in the context, please reply 'unanswerable', +Language: arabic, acc: 90.88%, prompt: Based on the context given, what is the clear key idea? If the answer is not in context, please reply 'unanswerable', +Language: arabic, acc: 90.48%, prompt: Based on the context, what is the most convincing explanation? If the answer is not available in the context, please reply 'unanswerable', +Language: arabic, acc: 90.88%, prompt: Based on the context, what is the most likely outcome? If the answer is not available in the context, please reply 'unanswerable', +Language: arabic, acc: 90.38%, prompt: Based on the context, which hypothesis is the most true? If the answer is not in context, please reply 'unanswerable', +Language: arabic, acc: 90.05%, prompt: From context, what is the most apparent factor influencing? If the answer is not available in the context, please reply 'unanswerable', +Language: arabic, acc: 90.05%, prompt: From context, provide the most accurate answer. If the answer is not in context, reply 'unanswerable', +Language: arabic, acc: 89.55%, prompt: From context, determine the most accurate answer. If the answer is not available in context, answer 'unanswerable', +Language: spanish, acc: 90.88%, prompt: Depending on the context, it provides the most precise answer. If the answer is not in context, answer with 'unanswerable'. +Language: spanish, acc: 90.88%, prompt: Briefly describes the situation and provides the corresponding response. If the answer cannot be found, answer with 'unanswerable'. +Language: spanish, acc: 90.88%, prompt: Given the information given, what is the most appropriate response? If the answer cannot be determined, answer with 'unanswerable'. +Language: spanish, acc: 90.05%, prompt: Read the following text and give the most accurate answer. If you can't find the answer, answer with 'unanswerable'. +Language: spanish, acc: 90.55%, prompt: Based on the description, what is the most accurate answer? If the answer is not found in the description, answer with 'unanswerable'. +Language: spanish, acc: 91.05%, prompt: From the context provided, which response is the most appropriate? If the answer cannot be found, answer with 'unanswerable'. +Language: spanish, acc: 89.55%, prompt: Analyze the following paragraph and provide the most accurate answer. If the answer is not in the paragraph, answer with 'unanswerable'. +Language: spanish, acc: 91.05%, prompt: According to the information presented, what is the most precise answer? If the answer cannot be determined, answer with 'unanswerable'. +Language: spanish, acc: 91.05%, prompt: After reading the excerpt, which do you think is the correct answer? If the answer cannot be discerned, answer with 'unanswerable'. +Language: spanish, acc: 90.88%, prompt: Based on the context, it provides the most appropriate response. If the answer is not in context, answer with 'unanswerable'. +Language: japanese, acc: 90.05%, prompt: Provide the most accurate answer from this context. If the answer isn't in the context, answer 'unanswerable'. +Language: japanese, acc: 90.99%, prompt: Please provide the most appropriate answer based on the information specified in this sentence. If the answer is not in the text, answer 'unanswerable'. +Language: japanese, acc: 90.55%, prompt: Please provide the most accurate answer based on the information guessed from this text. If the answer is not in the text, answer 'unanswerable'. +Language: japanese, acc: 89.48%, prompt: Provide the most detailed answer based on the given context. If the answer is not in the context, answer 'unanswerable'. +Language: japanese, acc: 89.55%, prompt: Consider the information derived from this context and provide the most accurate answer. If the answer is not in the context, answer 'unanswerable'. +Language: japanese, acc: 90.55%, prompt: Based on this context, please provide the most appropriate answer. If the answer is not in the context, answer 'unanswerable'. +Language: japanese, acc: 88.73%, prompt: Consider the information derived from the given text and provide the most detailed answer. If the answer is not in the text, please answer 'unanswerable'. +Language: japanese, acc: 90.05%, prompt: Provide the most accurate answer based on the information given in this text. If the answer is not in the text, answer 'unanswerable'. +Language: japanese, acc: 89.55%, prompt: Consider the information inferred from this context and provide the most appropriate answer. If the answer is not in the context, answer 'unanswerable'. +Language: japanese, acc: 89.98%, prompt: Provide the most detailed answer based on this context. If the answer is not in the context, answer 'unanswerable'. +Language: korean, acc: 90.05%, prompt: Give the most accurate answer in context. If the answer is not in context, respond with 'unanswerable'. +Language: korean, acc: 90.88%, prompt: Please provide additional information about the facts mentioned in this sentence. If no information is available, respond with 'unanswerable'. +Language: korean, acc: 90.88%, prompt: Please tell me what your question is about. If there is no context in which you can provide an answer, respond with 'unanswerable'. +Language: korean, acc: 90.88%, prompt: Please explain the concept mentioned in the following sentence. If there is no information on the concept, please respond with 'unanswerable'. +Language: korean, acc: 91.38%, prompt: Tell me what you're comparing to in this sentence. If nothing is compared, please respond with 'unanswerable'. +Language: korean, acc: 90.88%, prompt: Please perform the actions required by the following context. If the task is not possible or if you are not clear what needs to be done, respond with 'unanswerable'. +Language: korean, acc: 90.88%, prompt: Figure out what information this sentence contains. If no information is available, respond with 'unanswerable'. +Language: korean, acc: 91.05%, prompt: Please give a solution to what kind of problem in the following sentence. If there is no solution, respond with 'unanswerable'. +Language: korean, acc: 90.88%, prompt: Please give the cause of the incident mentioned in the context. If the cause is not clear, respond with 'unanswerable'. +Language: korean, acc: 90.38%, prompt: Give expected results in the following sentences. If the result is unpredictable, respond with 'unanswerable'. + +# iwslt + +## 10 prompts + +Acc: 0.27%, prompt: Accurately translate the sentence from {} to {}, ensuring the meaning remains intact. +Acc: 0.24%, prompt: Convert the following sentence from its original {} language to the target language {}. +Acc: 0.24%, prompt: Perform a machine translation for the provided sentence, changing it from {} to {}. +Acc: 0.24%, prompt: Using machine translation, convert the given sentence from {} into the {} language. +Acc: 0.24%, prompt: Please perform a translation of the given sentence, converting it from {} to {}. +Acc: 0.24%, prompt: Given the sentence below, perform a machine translation from {} to {}. +Acc: 0.24%, prompt: Translate the subsequent text passage from its original {} language to the {} language. +Acc: 0.24%, prompt: Translate the provided sentence from {} to {} while maintaining the original meaning and context. +Acc: 0.23%, prompt: Translate the subsequent sentence from its source language {} into the desired language {}. +Acc: 0.23%, prompt: Translate the following text from the source language {} to the target language {}. + +Acc: 0.27%, prompt: Taking on the role of a certified translator, perform a translation of the given sentence from {} to {}. +Acc: 0.27%, prompt: Assuming the responsibilities of a professional translator, translate the subsequent text passage from {} to {}. +Acc: 0.27%, prompt: As a language specialist, accurately translate the provided sentence from {} to {}. +Acc: 0.25%, prompt: As a qualified translator, convert the given sentence from its original {} language to the target language {}. +Acc: 0.24%, prompt: Assuming the role of an expert language translator, translate the given text from {} to {}. +Acc: 0.24%, prompt: As a skilled linguist, please convert the following sentence from {} to {}. +Acc: 0.24%, prompt: Acting as a professional translator, translate the provided sentence from {} to {}. +Acc: 0.24%, prompt: In the role of a language expert, perform a machine translation for the provided sentence, changing it from {} to {}. +Acc: 0.23%, prompt: While acting as an experienced language expert, translate the following text from {} to {}. +Acc: 0.23%, prompt: In the capacity of a proficient translator, please change the following sentence from {} to {}. + +## bertattack + +Original prompt: Accurately translate the sentence from {} to {}, ensuring the meaning remains intact. +Attacked prompt: b'i translate the sentence from {} to {}, assumed the meaning remains intact. ' +Original acc: 0.27%, attacked acc: 0.23%, dropped acc: 0.04% + +Original prompt: Convert the following sentence from its original {} language to the target language {}. +Attacked prompt: b'Convert the following sentence from its original {} language to the target language {}. ' +Original acc: 0.24%, attacked acc: 0.24%, dropped acc: 0.03% + +Original prompt: Perform a machine translation for the provided sentence, changing it from {} to {}. +Attacked prompt: b'create a machine translation for the provided verb, setting it from {} to {}. ' +Original acc: 0.24%, attacked acc: 0.23%, dropped acc: 0.01% + +Original prompt: Taking on the role of a certified translator, perform a translation of the given sentence from {} to {}. +Attacked prompt: b'she on the role of a certified translation, and a translation of the given sentence from {} to {}. ' +Original acc: 0.27%, attacked acc: 0.23%, dropped acc: 0.04% + +Original prompt: Assuming the responsibilities of a professional translator, translate the subsequent text passage from {} to {}. +Attacked prompt: b'Assuming the responsibilities of a professional syriac, translate the subsequent reading verse from {} to {}. ' +Original acc: 0.27%, attacked acc: 0.23%, dropped acc: 0.04% + +Original prompt: As a language specialist, accurately translate the provided sentence from {} to {}. +Attacked prompt: b'As a level specialist, just translate the provided sentence from {} to {}. ' +Original acc: 0.27%, attacked acc: 0.23%, dropped acc: 0.03% + +## checklist + +Original prompt: Accurately translate the sentence from {} to {}, ensuring the meaning remains intact. +Attacked prompt: b'Accurately translate the sentence from {} to {}, ensuring the meaning remains intact S6oUV5E54P. ' +Original acc: 0.27%, attacked acc: 0.24%, dropped acc: 0.03% + +Original prompt: Convert the following sentence from its original {} language to the target language {}. +Attacked prompt: b'Convert the following sentence from its original {} language to the target language lWJoGGRdjv {}. ' +Original acc: 0.24%, attacked acc: 0.19%, dropped acc: 0.05% + +Original prompt: Perform a machine translation for the provided sentence, changing it from {} to {}. +Attacked prompt: b'Perform a machine translation for the provided sentence, changing it from {} to mOJ9nEwT4f {}. ' +Original acc: 0.24%, attacked acc: 0.21%, dropped acc: 0.03% + +Original prompt: Taking on the role of a certified translator, perform a translation of the given sentence from {} to {}. +Attacked prompt: b'Taking on the role of a certified translator, perform a translation of the given sentence from {} to njCuciQJpB {}. ' +Original acc: 0.27%, attacked acc: 0.23%, dropped acc: 0.04% + +Original prompt: Assuming the responsibilities of a professional translator, translate the subsequent text passage from {} to {}. +Attacked prompt: b'Assuming the responsibilities of a professional translator, translate the subsequent text passage from {} to xikCjkMydH {}. ' +Original acc: 0.27%, attacked acc: 0.23%, dropped acc: 0.04% + +Original prompt: As a language specialist, accurately translate the provided sentence from {} to {}. +Attacked prompt: b'As a language specialist, accurately translate the provided sentence from {} to g0vBZf3tQC {}. ' +Original acc: 0.27%, attacked acc: 0.23%, dropped acc: 0.04% + +## deepwordbug + +Original prompt: Accurately translate the sentence from {} to {}, ensuring the meaning remains intact. +Attacked prompt: b'Accurately translate the seneence from {} to {}, enusring the emaning remaiOs intat. ' +Original acc: 0.27%, attacked acc: 0.23%, dropped acc: 0.04% + +Original prompt: Convert the following sentence from its original {} language to the target language {}. +Attacked prompt: b'Convert the following sentence from its original {} language to the target language {}. ' +Original acc: 0.24%, attacked acc: 0.24%, dropped acc: 0.03% + +Original prompt: Perform a machine translation for the provided sentence, changing it from {} to {}. +Attacked prompt: b'Preform a machine translatino for the provied senteXce, chanigng it from {} to {}. ' +Original acc: 0.24%, attacked acc: 0.19%, dropped acc: 0.05% + +Original prompt: Taking on the role of a certified translator, perform a translation of the given sentence from {} to {}. +Attacked prompt: b'Tking on the role of a Aertified tranolator, pefrorm a transAlation of the gUven sentence from {} to {}. ' +Original acc: 0.27%, attacked acc: 0.21%, dropped acc: 0.06% + +Original prompt: Assuming the responsibilities of a professional translator, translate the subsequent text passage from {} to {}. +Attacked prompt: b'Assuming the responsibiljities of a professional translaZor, translate the subsequnet Gext pSssage from {} to {}. ' +Original acc: 0.27%, attacked acc: 0.23%, dropped acc: 0.04% + +Original prompt: As a language specialist, accurately translate the provided sentence from {} to {}. +Attacked prompt: b'sA a languAage specialits, accurtely translate the prpvided senpence from {} to {}. ' +Original acc: 0.27%, attacked acc: 0.21%, dropped acc: 0.05% + +## stresstest + +Original prompt: Accurately translate the sentence from {} to {}, ensuring the meaning remains intact. +Attacked prompt: b'Accurately translate the sentence from {} to {}, ensuring the meaning remains intact and true is true and true is true and true is true and true is true and true is true . ' +Original acc: 0.27%, attacked acc: 0.24%, dropped acc: 0.03% + +Original prompt: Convert the following sentence from its original {} language to the target language {}. +Attacked prompt: b'Convert the following sentence from its original {} language to the target language and true is true {}. ' +Original acc: 0.24%, attacked acc: 0.20%, dropped acc: 0.04% + +Original prompt: Perform a machine translation for the provided sentence, changing it from {} to {}. +Attacked prompt: b'Perform a machine translation for the provided sentence, changing it from {} to and true is true and true is true and true is true and true is true and true is true {}. ' +Original acc: 0.24%, attacked acc: 0.19%, dropped acc: 0.05% + +Original prompt: Taking on the role of a certified translator, perform a translation of the given sentence from {} to {}. +Attacked prompt: b'Taking on the role of a certified translator, perform a translation of the given sentence from {} to and true is true and true is true and true is true and true is true and true is true {}. ' +Original acc: 0.27%, attacked acc: 0.19%, dropped acc: 0.08% + +Original prompt: Assuming the responsibilities of a professional translator, translate the subsequent text passage from {} to {}. +Attacked prompt: b'Assuming the responsibilities of a professional translator, translate the subsequent text passage from {} to and true is true and true is true and true is true and true is true and true is true {}. ' +Original acc: 0.27%, attacked acc: 0.19%, dropped acc: 0.08% + +Original prompt: As a language specialist, accurately translate the provided sentence from {} to {}. +Attacked prompt: b'As a language specialist, accurately translate the provided sentence from {} to and true is true and true is true and true is true and true is true and true is true {}. ' +Original acc: 0.27%, attacked acc: 0.20%, dropped acc: 0.07% + +## textbugger + +Original prompt: Accurately translate the sentence from {} to {}, ensuring the meaning remains intact. +Attacked prompt: b'Ac\xcf\xb2urately translate the sentence from {} to {}, ensuring the meaning remains unaffected. ' +Original acc: 0.27%, attacked acc: 0.23%, dropped acc: 0.04% + +Original prompt: Convert the following sentence from its original {} language to the target language {}. +Attacked prompt: b'Convert the following sentence from its original {} language to the target language {}. ' +Original acc: 0.24%, attacked acc: 0.24%, dropped acc: 0.03% + +Original prompt: Perform a machine translation for the provided sentence, changing it from {} to {}. +Attacked prompt: b'Perfo\xe2\xb2\x85m a machine translation for the provided sent\xd0\xb5nce, changing it from {} to {}. ' +Original acc: 0.24%, attacked acc: 0.23%, dropped acc: 0.01% + +Original prompt: Taking on the role of a certified translator, perform a translation of the given sentence from {} to {}. +Attacked prompt: b'Taking on the role of a certifying translators, pefrorm a translati\xd0\xben of the giv\xd0\xb5n sentence from {} to {}. ' +Original acc: 0.27%, attacked acc: 0.23%, dropped acc: 0.04% + +Original prompt: Assuming the responsibilities of a professional translator, translate the subsequent text passage from {} to {}. +Attacked prompt: b'As suming the responsibilities of a professional tra\xd5\xb8slator, translate the subsequent text passage from {} to {}. ' +Original acc: 0.27%, attacked acc: 0.23%, dropped acc: 0.04% + +Original prompt: As a language specialist, accurately translate the provided sentence from {} to {}. +Attacked prompt: b'As a languag\xd0\xb5 speciali\xd1\x95t, accurately translate the provided sentence from {} to {}. ' +Original acc: 0.27%, attacked acc: 0.24%, dropped acc: 0.03% + +## textfooler + +Original prompt: Accurately translate the sentence from {} to {}, ensuring the meaning remains intact. +Attacked prompt: b'Rightly translate the convicts from {} to {}, insurance the signify sojourn unaffected. ' +Original acc: 0.27%, attacked acc: 0.19%, dropped acc: 0.08% + +Original prompt: Convert the following sentence from its original {} language to the target language {}. +Attacked prompt: b'Convert the following sentence from its original {} language to the target language {}. ' +Original acc: 0.24%, attacked acc: 0.24%, dropped acc: 0.03% + +Original prompt: Perform a machine translation for the provided sentence, changing it from {} to {}. +Attacked prompt: b'Achieving a equipment translation for the provided chastisement, adaptations it from {} to {}. ' +Original acc: 0.24%, attacked acc: 0.19%, dropped acc: 0.05% + +Original prompt: Taking on the role of a certified translator, perform a translation of the given sentence from {} to {}. +Attacked prompt: b'Taking on the role of a certified translator, satisfy a converting of the given sentence from {} to {}. ' +Original acc: 0.27%, attacked acc: 0.23%, dropped acc: 0.04% + +Original prompt: Assuming the responsibilities of a professional translator, translate the subsequent text passage from {} to {}. +Attacked prompt: b'Adopt the indebted of a vocational artist, translate the subsequent laws transition from {} to {}. ' +Original acc: 0.27%, attacked acc: 0.19%, dropped acc: 0.08% + +Original prompt: As a language specialist, accurately translate the provided sentence from {} to {}. +Attacked prompt: b'Oj a terminology scholar, rightly translate the afforded sorrows from {} to {}. ' +Original acc: 0.27%, attacked acc: 0.19%, dropped acc: 0.08% + +## translation + +Language: chinese, acc: 0.23%, prompt: Please translate the given sentence into {} to {}. +Language: chinese, acc: 0.23%, prompt: Please translate the following sentences from {} to {}. +Language: chinese, acc: 0.23%, prompt: Please convert the following sentences to {} and translate to {}. +Language: chinese, acc: 0.24%, prompt: Please convert the given sentence from {} to {}. +Language: chinese, acc: 0.22%, prompt: Please translate the next sentence from {} to {}. +Language: chinese, acc: 0.23%, prompt: Please translate the following sentence from {} to {}. +Language: chinese, acc: 0.24%, prompt: Please translate the sentences given into {} and convert them into {}. +Language: chinese, acc: 0.24%, prompt: Please convert the sentences given to {} to {}. +Language: chinese, acc: 0.24%, prompt: Please translate the following sentences into {} and convert them into {}. +Language: chinese, acc: 0.23%, prompt: Please change the given sentence from {} to {}. +Language: french, acc: 0.24%, prompt: Please translate the given sentence, converting it from {} to {}. +Language: french, acc: 0.23%, prompt: Please translate the following sentence from {} to {}. +Language: french, acc: 0.23%, prompt: Please turn the sentence below into {}, then translate it into {}. +Language: french, acc: 0.24%, prompt: Please convert the given phrase from {} to {}. +Language: french, acc: 0.23%, prompt: Please translate the following sentence from {} to {}. +Language: french, acc: 0.23%, prompt: Please translate the sentence below from {} to {}. +Language: french, acc: 0.24%, prompt: Please translate the given sentence to {}, then convert it to {}. +Language: french, acc: 0.24%, prompt: Please make a translation of the supplied sentence, transforming it from {} to {}. +Language: french, acc: 0.24%, prompt: Please translate the following sentence to {}, then convert it to {}. +Language: french, acc: 0.24%, prompt: Please transform the given sentence from {} to {}. +Language: arabic, acc: 0.24%, prompt: Please translate the given sentence, and convert it from {} to {}, +Language: arabic, acc: 0.23%, prompt: Please translate the following sentence from {} to {}, +Language: arabic, acc: 0.23%, prompt: Please convert the sentence below to {}, and then translate it to {}, +Language: arabic, acc: 0.23%, prompt: Please convert the given sentence from {} to {}, +Language: arabic, acc: 0.23%, prompt: Please translate the following sentence from {} to {}, +Language: arabic, acc: 0.23%, prompt: Please convert the sentence below from {} to {}, +Language: arabic, acc: 0.24%, prompt: Please translate the given sentence to {}, then convert it to {}, +Language: arabic, acc: 0.24%, prompt: Please translate the given sentence, and convert it from {} to {}, +Language: arabic, acc: 0.24%, prompt: Please translate to {}, then convert to {}, +Language: arabic, acc: 0.24%, prompt: Please convert the given sentence from {} to {}. +Language: spanish, acc: 0.24%, prompt: Please make a translation of the provided phrase, converting it from {} to {}. +Language: spanish, acc: 0.23%, prompt: Please translate the following sentence from {} to {}. +Language: spanish, acc: 0.23%, prompt: Please convert the next sentence to {}, and then translate it to {}. +Language: spanish, acc: 0.24%, prompt: Please make a translation of the given phrase, converting it from {} to {}. +Language: spanish, acc: 0.23%, prompt: Please translate the following sentence from {} to {}. +Language: spanish, acc: 0.23%, prompt: Please convert the following sentence from {} to {}. +Language: spanish, acc: 0.24%, prompt: Please translate the sentence provided to {}, and then turn it to {}. +Language: spanish, acc: 0.24%, prompt: Please make a translation of the following sentence, converting it from {} to {}. +Language: spanish, acc: 0.23%, prompt: Please translate the next sentence to {}, and then turn it to {}. +Language: spanish, acc: 0.24%, prompt: Please convert the given sentence from {} to {}. +Language: japanese, acc: 0.23%, prompt: Please translate the given sentence from {} to {}. +Language: japanese, acc: 0.23%, prompt: Please translate the following sentence from {} to {}. +Language: japanese, acc: 0.23%, prompt: Please convert the following sentences into {} and translate them into {}. +Language: japanese, acc: 0.24%, prompt: Please translate the given sentence by converting {} to {}. +Language: japanese, acc: 0.23%, prompt: Please translate the following sentence from {} to {}. +Language: japanese, acc: 0.24%, prompt: Please convert the following sentences from {} to {}. +Language: japanese, acc: 0.23%, prompt: Translate the given sentence into {} and convert it to {}. +Language: japanese, acc: 0.23%, prompt: Please translate the given sentence from {} to {}. +Language: japanese, acc: 0.24%, prompt: Translate the following sentence into {} and convert it to {}. +Language: japanese, acc: 0.24%, prompt: Convert the given statement from {} to {}. +Language: korean, acc: 0.23%, prompt: Please translate the given sentence from {} to {}. +Language: korean, acc: 0.23%, prompt: Please translate the following sentence from {} to {}. +Language: korean, acc: 0.23%, prompt: Please translate the sentences below into {}, then {}. +Language: korean, acc: 0.23%, prompt: Please translate the given sentences from {} to {}. +Language: korean, acc: 0.23%, prompt: Please translate the following sentence from {} to {}. +Language: korean, acc: 0.24%, prompt: Please convert the sentences below from {} to {}. +Language: korean, acc: 0.23%, prompt: Please translate the given sentence into {}, then {}. +Language: korean, acc: 0.23%, prompt: Please translate the given sentence from {} to {}. +Language: korean, acc: 0.23%, prompt: Please translate the following sentences into {}, then {}. +Language: korean, acc: 0.24%, prompt: Please convert the given sentence from {} to {}. + +# un_multi + +## 10 prompts + +Acc: 0.36%, prompt: Perform a machine translation for the provided sentence, changing it from {} to {}. +Acc: 0.36%, prompt: Given the sentence below, perform a machine translation from {} to {}. +Acc: 0.36%, prompt: Translate the subsequent sentence from its source language {} into the desired language {}. +Acc: 0.36%, prompt: Translate the subsequent text passage from its original {} language to the {} language. +Acc: 0.36%, prompt: Translate the provided sentence from {} to {} while maintaining the original meaning and context. +Acc: 0.36%, prompt: Accurately translate the sentence from {} to {}, ensuring the meaning remains intact. +Acc: 0.35%, prompt: Using machine translation, convert the given sentence from {} into the {} language. +Acc: 0.35%, prompt: Translate the following text from the source language {} to the target language {}. +Acc: 0.35%, prompt: Please perform a translation of the given sentence, converting it from {} to {}. +Acc: 0.35%, prompt: Convert the following sentence from its original {} language to the target language {}. + +Acc: 0.36%, prompt: As a skilled linguist, please convert the following sentence from {} to {}. +Acc: 0.36%, prompt: In the capacity of a proficient translator, please change the following sentence from {} to {}. +Acc: 0.36%, prompt: Acting as a professional translator, translate the provided sentence from {} to {}. +Acc: 0.36%, prompt: As a language specialist, accurately translate the provided sentence from {} to {}. +Acc: 0.36%, prompt: While acting as an experienced language expert, translate the following text from {} to {}. +Acc: 0.36%, prompt: In the role of a language expert, perform a machine translation for the provided sentence, changing it from {} to {}. +Acc: 0.36%, prompt: Assuming the responsibilities of a professional translator, translate the subsequent text passage from {} to {}. +Acc: 0.36%, prompt: Assuming the role of an expert language translator, translate the given text from {} to {}. +Acc: 0.35%, prompt: Taking on the role of a certified translator, perform a translation of the given sentence from {} to {}. +Acc: 0.35%, prompt: As a qualified translator, convert the given sentence from its original {} language to the target language {}. + +## bertattack + +Original prompt: Perform a machine translation for the provided sentence, changing it from {} to {}. +Attacked prompt: b'perform a machine translation for the displayed sentence, export it from {} to {}. ' +Original acc: 0.36%, attacked acc: 0.35%, dropped acc: 0.01% + +Original prompt: Given the sentence below, perform a machine translation from {} to {}. +Attacked prompt: b'Given the sentence below, for a machine operator from {} to {}. ' +Original acc: 0.36%, attacked acc: 0.35%, dropped acc: 0.00% + +Original prompt: Translate the subsequent sentence from its source language {} into the desired language {}. +Attacked prompt: b'Translate the later sentence from its source rule {} into the desired language {}. ' +Original acc: 0.36%, attacked acc: 0.35%, dropped acc: 0.01% + +Original prompt: As a skilled linguist, please convert the following sentence from {} to {}. +Attacked prompt: b'd a skilled linguist, right example the following sentence from {} to {}. ' +Original acc: 0.36%, attacked acc: 0.35%, dropped acc: 0.01% + +Original prompt: In the capacity of a proficient translator, please change the following sentence from {} to {}. +Attacked prompt: b'if the capacity of a capable translator, leave changed the following sentence from {} to {}. ' +Original acc: 0.36%, attacked acc: 0.35%, dropped acc: 0.01% + +Original prompt: Acting as a professional translator, translate the provided sentence from {} to {}. +Attacked prompt: b'his as a qualified translator, translate the provided sentence from {} to {}. ' +Original acc: 0.36%, attacked acc: 0.35%, dropped acc: 0.01% + +## checklist + +Original prompt: Perform a machine translation for the provided sentence, changing it from {} to {}. +Attacked prompt: b'Perform a machine translation for the provided sentence, changing it from {} to EAB4KP2NVY {}. ' +Original acc: 0.36%, attacked acc: 0.35%, dropped acc: 0.01% + +Original prompt: Given the sentence below, perform a machine translation from {} to {}. +Attacked prompt: b'Given the sentence below, perform a machine translation from {} to Kw6nrs57gH {}. ' +Original acc: 0.36%, attacked acc: 0.35%, dropped acc: 0.01% + +Original prompt: Translate the subsequent sentence from its source language {} into the desired language {}. +Attacked prompt: b'Translate the subsequent sentence from its source language {} into the desired language 5XeflW1ZJc {}. ' +Original acc: 0.36%, attacked acc: 0.35%, dropped acc: 0.00% + +Original prompt: As a skilled linguist, please convert the following sentence from {} to {}. +Attacked prompt: b'As a skilled linguist, please convert the following sentence from {} to AMsRIKZniY {}. ' +Original acc: 0.36%, attacked acc: 0.35%, dropped acc: 0.01% + +Original prompt: In the capacity of a proficient translator, please change the following sentence from {} to {}. +Attacked prompt: b'In the capacity of a proficient translator, please change the following sentence from {} to vTAjHynoIG {}. ' +Original acc: 0.36%, attacked acc: 0.35%, dropped acc: 0.01% + +Original prompt: Acting as a professional translator, translate the provided sentence from {} to {}. +Attacked prompt: b'Acting as a professional translator, translate the provided sentence from {} to vTAjHynoIG {}. ' +Original acc: 0.36%, attacked acc: 0.35%, dropped acc: 0.01% + +## deepwordbug + +Original prompt: Perform a machine translation for the provided sentence, changing it from {} to {}. +Attacked prompt: b'PeVform a machine transAation for the provide setence, changlng it from {} to {}. ' +Original acc: 0.36%, attacked acc: 0.35%, dropped acc: 0.01% + +Original prompt: Given the sentence below, perform a machine translation from {} to {}. +Attacked prompt: b'Gvien the sentence below, perform a machine translation from {} to {}. ' +Original acc: 0.36%, attacked acc: 0.35%, dropped acc: 0.00% + +Original prompt: Translate the subsequent sentence from its source language {} into the desired language {}. +Attacked prompt: b'Translate the subsMquent sentejce from its source lasguage {} into the desired glanguage {}. ' +Original acc: 0.36%, attacked acc: 0.35%, dropped acc: 0.00% + +Original prompt: As a skilled linguist, please convert the following sentence from {} to {}. +Attacked prompt: b'AK a skilled linguist, please onvert the following sentence from {} to {}. ' +Original acc: 0.36%, attacked acc: 0.35%, dropped acc: 0.01% + +Original prompt: In the capacity of a proficient translator, please change the following sentence from {} to {}. +Attacked prompt: b'n the capaciyt of a proficient translator, Pplease chagne the following sentence from {} to {}. ' +Original acc: 0.36%, attacked acc: 0.35%, dropped acc: 0.01% + +Original prompt: Acting as a professional translator, translate the provided sentence from {} to {}. +Attacked prompt: b'cAting as a professional transaltor, translate the provided sentence from {} to {}. ' +Original acc: 0.36%, attacked acc: 0.35%, dropped acc: 0.00% + +## stresstest + +Original prompt: Perform a machine translation for the provided sentence, changing it from {} to {}. +Attacked prompt: b'Perform a machine translation for the provided sentence, changing it from {} to and false is not true {}. ' +Original acc: 0.36%, attacked acc: 0.35%, dropped acc: 0.00% + +Original prompt: Given the sentence below, perform a machine translation from {} to {}. +Attacked prompt: b'Given the sentence below, perform a machine translation from {} to and true is true {}. ' +Original acc: 0.36%, attacked acc: 0.35%, dropped acc: 0.00% + +Original prompt: Translate the subsequent sentence from its source language {} into the desired language {}. +Attacked prompt: b'Translate the subsequent sentence from its source language {} into the desired language and false is not true {}. ' +Original acc: 0.36%, attacked acc: 0.35%, dropped acc: 0.00% + +Original prompt: As a skilled linguist, please convert the following sentence from {} to {}. +Attacked prompt: b'As a skilled linguist, please convert the following sentence from {} to and true is true {}. ' +Original acc: 0.36%, attacked acc: 0.35%, dropped acc: 0.01% + +Original prompt: In the capacity of a proficient translator, please change the following sentence from {} to {}. +Attacked prompt: b'In the capacity of a proficient translator, please change the following sentence from {} to and false is not true {}. ' +Original acc: 0.36%, attacked acc: 0.35%, dropped acc: 0.00% + +Original prompt: Acting as a professional translator, translate the provided sentence from {} to {}. +Attacked prompt: b'Acting as a professional translator, translate the provided sentence from {} to and true is true and true is true and true is true and true is true and true is true {}. ' +Original acc: 0.36%, attacked acc: 0.35%, dropped acc: 0.00% + +## textbugger + +Original prompt: Perform a machine translation for the provided sentence, changing it from {} to {}. +Attacked prompt: b'Preform a machinery translation for the provid\xd0\xb5d sentence, changing it from {} to {}. ' +Original acc: 0.36%, attacked acc: 0.35%, dropped acc: 0.01% + +Original prompt: Given the sentence below, perform a machine translation from {} to {}. +Attacked prompt: b'Given the sentence below, perform a equipment translators from {} to {}. ' +Original acc: 0.36%, attacked acc: 0.35%, dropped acc: 0.01% + +Original prompt: Translate the subsequent sentence from its source language {} into the desired language {}. +Attacked prompt: b'Translate the subsequent condemnation from its source language {} into the desired language {}. ' +Original acc: 0.36%, attacked acc: 0.35%, dropped acc: 0.00% + +Original prompt: As a skilled linguist, please convert the following sentence from {} to {}. +Attacked prompt: b'As a skillful linguist, pelase conv\xd0\xb5rt the following sentence from {} to {}. ' +Original acc: 0.36%, attacked acc: 0.35%, dropped acc: 0.01% + +Original prompt: In the capacity of a proficient translator, please change the following sentence from {} to {}. +Attacked prompt: b'In the capacity of a proficient translator, please change the following snetence from {} to {}. ' +Original acc: 0.36%, attacked acc: 0.35%, dropped acc: 0.00% + +Original prompt: Acting as a professional translator, translate the provided sentence from {} to {}. +Attacked prompt: b'Acting as a professional tra\xd5\xb8slator, translate the \xd1\x80rovided sentence from {} to {}. ' +Original acc: 0.36%, attacked acc: 0.35%, dropped acc: 0.01% + +## textfooler + +Original prompt: Perform a machine translation for the provided sentence, changing it from {} to {}. +Attacked prompt: b'Perform a computer translate for the tabled sentence, changing it from {} to {}. ' +Original acc: 0.36%, attacked acc: 0.35%, dropped acc: 0.01% + +Original prompt: Given the sentence below, perform a machine translation from {} to {}. +Attacked prompt: b'Given the sorrows below, fulfillment a device translation from {} to {}. ' +Original acc: 0.36%, attacked acc: 0.35%, dropped acc: 0.01% + +Original prompt: Translate the subsequent sentence from its source language {} into the desired language {}. +Attacked prompt: b'Translate the forth sanction from its source dictionary {} into the desired language {}. ' +Original acc: 0.36%, attacked acc: 0.35%, dropped acc: 0.01% + +Original prompt: As a skilled linguist, please convert the following sentence from {} to {}. +Attacked prompt: b'As a skilled linguist, please translate the following punishment from {} to {}. ' +Original acc: 0.36%, attacked acc: 0.35%, dropped acc: 0.01% + +Original prompt: In the capacity of a proficient translator, please change the following sentence from {} to {}. +Attacked prompt: b'In the ability of a proficient translator, please variant the following pity from {} to {}. ' +Original acc: 0.36%, attacked acc: 0.35%, dropped acc: 0.01% + +Original prompt: Acting as a professional translator, translate the provided sentence from {} to {}. +Attacked prompt: b'Acting as a professional artists, translate the envisaged sentence from {} to {}. ' +Original acc: 0.36%, attacked acc: 0.35%, dropped acc: 0.01% + +## translation + +Language: chinese, acc: 0.36%, prompt: Please translate the given sentence into {} to {}. +Language: chinese, acc: 0.36%, prompt: Please translate the following sentences from {} to {}. +Language: chinese, acc: 0.35%, prompt: Please convert the following sentences to {} and translate to {}. +Language: chinese, acc: 0.36%, prompt: Please convert the given sentence from {} to {}. +Language: chinese, acc: 0.35%, prompt: Please translate the next sentence from {} to {}. +Language: chinese, acc: 0.35%, prompt: Please translate the following sentence from {} to {}. +Language: chinese, acc: 0.36%, prompt: Please translate the sentences given into {} and convert them into {}. +Language: chinese, acc: 0.36%, prompt: Please convert the sentences given to {} to {}. +Language: chinese, acc: 0.36%, prompt: Please translate the following sentences into {} and convert them into {}. +Language: chinese, acc: 0.36%, prompt: Please change the given sentence from {} to {}. +Language: french, acc: 0.36%, prompt: Please translate the given sentence, converting it from {} to {}. +Language: french, acc: 0.35%, prompt: Please translate the following sentence from {} to {}. +Language: french, acc: 0.36%, prompt: Please turn the sentence below into {}, then translate it into {}. +Language: french, acc: 0.36%, prompt: Please convert the given phrase from {} to {}. +Language: french, acc: 0.35%, prompt: Please translate the following sentence from {} to {}. +Language: french, acc: 0.36%, prompt: Please translate the sentence below from {} to {}. +Language: french, acc: 0.36%, prompt: Please translate the given sentence to {}, then convert it to {}. +Language: french, acc: 0.35%, prompt: Please make a translation of the supplied sentence, transforming it from {} to {}. +Language: french, acc: 0.36%, prompt: Please translate the following sentence to {}, then convert it to {}. +Language: french, acc: 0.36%, prompt: Please transform the given sentence from {} to {}. +Language: arabic, acc: 0.36%, prompt: Please translate the given sentence, and convert it from {} to {}, +Language: arabic, acc: 0.35%, prompt: Please translate the following sentence from {} to {}, +Language: arabic, acc: 0.35%, prompt: Please convert the sentence below to {}, and then translate it to {}, +Language: arabic, acc: 0.36%, prompt: Please convert the given sentence from {} to {}, +Language: arabic, acc: 0.35%, prompt: Please translate the following sentence from {} to {}, +Language: arabic, acc: 0.35%, prompt: Please convert the sentence below from {} to {}, +Language: arabic, acc: 0.36%, prompt: Please translate the given sentence to {}, then convert it to {}, +Language: arabic, acc: 0.36%, prompt: Please translate the given sentence, and convert it from {} to {}, +Language: arabic, acc: 0.36%, prompt: Please translate to {}, then convert to {}, +Language: arabic, acc: 0.36%, prompt: Please convert the given sentence from {} to {}. +Language: spanish, acc: 0.36%, prompt: Please make a translation of the provided phrase, converting it from {} to {}. +Language: spanish, acc: 0.35%, prompt: Please translate the following sentence from {} to {}. +Language: spanish, acc: 0.35%, prompt: Please convert the next sentence to {}, and then translate it to {}. +Language: spanish, acc: 0.36%, prompt: Please make a translation of the given phrase, converting it from {} to {}. +Language: spanish, acc: 0.35%, prompt: Please translate the following sentence from {} to {}. +Language: spanish, acc: 0.35%, prompt: Please convert the following sentence from {} to {}. +Language: spanish, acc: 0.36%, prompt: Please translate the sentence provided to {}, and then turn it to {}. +Language: spanish, acc: 0.36%, prompt: Please make a translation of the following sentence, converting it from {} to {}. +Language: spanish, acc: 0.35%, prompt: Please translate the next sentence to {}, and then turn it to {}. +Language: spanish, acc: 0.36%, prompt: Please convert the given sentence from {} to {}. +Language: japanese, acc: 0.36%, prompt: Please translate the given sentence from {} to {}. +Language: japanese, acc: 0.35%, prompt: Please translate the following sentence from {} to {}. +Language: japanese, acc: 0.35%, prompt: Please convert the following sentences into {} and translate them into {}. +Language: japanese, acc: 0.36%, prompt: Please translate the given sentence by converting {} to {}. +Language: japanese, acc: 0.35%, prompt: Please translate the following sentence from {} to {}. +Language: japanese, acc: 0.36%, prompt: Please convert the following sentences from {} to {}. +Language: japanese, acc: 0.35%, prompt: Translate the given sentence into {} and convert it to {}. +Language: japanese, acc: 0.36%, prompt: Please translate the given sentence from {} to {}. +Language: japanese, acc: 0.36%, prompt: Translate the following sentence into {} and convert it to {}. +Language: japanese, acc: 0.35%, prompt: Convert the given statement from {} to {}. +Language: korean, acc: 0.36%, prompt: Please translate the given sentence from {} to {}. +Language: korean, acc: 0.35%, prompt: Please translate the following sentence from {} to {}. +Language: korean, acc: 0.35%, prompt: Please translate the sentences below into {}, then {}. +Language: korean, acc: 0.36%, prompt: Please translate the given sentences from {} to {}. +Language: korean, acc: 0.35%, prompt: Please translate the following sentence from {} to {}. +Language: korean, acc: 0.36%, prompt: Please convert the sentences below from {} to {}. +Language: korean, acc: 0.35%, prompt: Please translate the given sentence into {}, then {}. +Language: korean, acc: 0.36%, prompt: Please translate the given sentence from {} to {}. +Language: korean, acc: 0.35%, prompt: Please translate the following sentences into {}, then {}. +Language: korean, acc: 0.36%, prompt: Please convert the given sentence from {} to {}. + +# math + +## 10 prompts + +Acc: 16.88%, prompt: Figure out the solution for the following mathematical task with {}. +Acc: 16.25%, prompt: Solve the following math question about {}. +Acc: 16.25%, prompt: Calculate the answer to the following math query about {}. +Acc: 16.25%, prompt: Compute the result of this math task concerning {}. +Acc: 16.25%, prompt: Resolve the following mathematical question associated with {}. +Acc: 16.25%, prompt: Obtain the result for this math question regarding {}. +Acc: 16.25%, prompt: Evaluate the following mathematical problem that includes {}. +Acc: 15.62%, prompt: Determine the solution to this mathematical problem related to {}. +Acc: 15.62%, prompt: Find the solution for this mathematical challenge with {}. +Acc: 15.62%, prompt: Work out the answer to this math problem featuring {}. + +Acc: 16.88%, prompt: Pretend you are a math teacher and solve this mathematical question concerning {}. +Acc: 16.25%, prompt: Act as a math expert and compute the result of the following mathematical task about {}. +Acc: 16.25%, prompt: As a mathematics consultant, resolve the following problem associated with {}. +Acc: 16.25%, prompt: In the shoes of a mathematics master, obtain the result for this math question that includes {}. +Acc: 15.62%, prompt: Imagine being a math mentor and determine the solution to the following problem with {}. +Acc: 15.62%, prompt: In the position of a mathematics coach, figure out the answer to this math challenge involving {}. +Acc: 15.62%, prompt: As a math guru, evaluate the following mathematical task regarding {}. +Acc: 15.00%, prompt: As a mathematics instructor, calculate the answer to the following problem related to {}. +Acc: 15.00%, prompt: Taking on the role of a math specialist, work out the solution for this mathematical question featuring {}. +Acc: 14.37%, prompt: Embodying a mathematics advisor, find the answer to the following math problem with {}. + +## bertattack + +Original prompt: Figure out the solution for the following mathematical task with {}. +Attacked prompt: b'Figure out the solution for the following arithmetic task with {}. ' +Original acc: 16.88%, attacked acc: 13.75%, dropped acc: 3.12% + +Original prompt: Solve the following math question about {}. +Attacked prompt: b'if the following math question about {}. ' +Original acc: 16.25%, attacked acc: 15.00%, dropped acc: 1.25% + +Original prompt: Calculate the answer to the following math query about {}. +Attacked prompt: b'if the answer to the following math query about {}. ' +Original acc: 16.25%, attacked acc: 13.75%, dropped acc: 2.50% + +Original prompt: Pretend you are a math teacher and solve this mathematical question concerning {}. +Attacked prompt: b'Pretend you are a math teacher and solve this correct table concerning {}. ' +Original acc: 16.88%, attacked acc: 14.37%, dropped acc: 2.50% + +Original prompt: Act as a math expert and compute the result of the following mathematical task about {}. +Attacked prompt: b'Act as a math team and correct the result of the following mathematical task about {}. ' +Original acc: 16.25%, attacked acc: 12.50%, dropped acc: 3.75% + +Original prompt: As a mathematics consultant, resolve the following problem associated with {}. +Attacked prompt: b'and a mathematics consultant, identify the following problem associated with {}. ' +Original acc: 16.25%, attacked acc: 14.37%, dropped acc: 1.88% + +## checklist + +Original prompt: Figure out the solution for the following mathematical task with {}. +Attacked prompt: b'Figure out the solution for the following mathematical task with LkF0FZxMZ4 {}. ' +Original acc: 16.88%, attacked acc: 15.00%, dropped acc: 1.88% + +Original prompt: Solve the following math question about {}. +Attacked prompt: b'Solve the following math question about Cev0s49fbe {}. ' +Original acc: 16.25%, attacked acc: 15.62%, dropped acc: 0.63% + +Original prompt: Calculate the answer to the following math query about {}. +Attacked prompt: b'Calculate the answer to the following math query about 5XeflW1ZJc {}. ' +Original acc: 16.25%, attacked acc: 15.62%, dropped acc: 0.63% + +Original prompt: Pretend you are a math teacher and solve this mathematical question concerning {}. +Attacked prompt: b'Pretend you are a math teacher and solve this mathematical question concerning 5XeflW1ZJc {}. ' +Original acc: 16.88%, attacked acc: 16.25%, dropped acc: 0.63% + +Original prompt: Act as a math expert and compute the result of the following mathematical task about {}. +Attacked prompt: b'Act as a math expert and compute the result of the following mathematical task about 5XeflW1ZJc {}. ' +Original acc: 16.25%, attacked acc: 15.00%, dropped acc: 1.25% + +Original prompt: As a mathematics consultant, resolve the following problem associated with {}. +Attacked prompt: b'As a mathematics consultant, resolve the following problem associated with EAB4KP2NVY {}. ' +Original acc: 16.25%, attacked acc: 16.25%, dropped acc: 0.00% + +## deepwordbug + +Original prompt: Figure out the solution for the following mathematical task with {}. +Attacked prompt: b'Figure out the solution for the following maKthematical Utask with {}. ' +Original acc: 16.88%, attacked acc: 14.37%, dropped acc: 2.50% + +Original prompt: Solve the following math question about {}. +Attacked prompt: b'Solve the following math question about {}. ' +Original acc: 16.25%, attacked acc: 16.25%, dropped acc: 0.63% + +Original prompt: Calculate the answer to the following math query about {}. +Attacked prompt: b'Calculate the answer to the followng math query about {}. ' +Original acc: 16.25%, attacked acc: 15.62%, dropped acc: 0.63% + +Original prompt: Pretend you are a math teacher and solve this mathematical question concerning {}. +Attacked prompt: b'Petend you are a math teacher and solve this mathematical euestion concCerning {}. ' +Original acc: 16.88%, attacked acc: 15.00%, dropped acc: 1.88% + +Original prompt: Act as a math expert and compute the result of the following mathematical task about {}. +Attacked prompt: b'Act as a math expret and compute the result of the following mathematical task about {}. ' +Original acc: 16.25%, attacked acc: 15.00%, dropped acc: 1.25% + +Original prompt: As a mathematics consultant, resolve the following problem associated with {}. +Attacked prompt: b'A a mathematics consultant, resolve the following problem associated with {}. ' +Original acc: 16.25%, attacked acc: 15.00%, dropped acc: 1.25% + +## stresstest + +Original prompt: Figure out the solution for the following mathematical task with {}. +Attacked prompt: b'Figure out the solution for the following mathematical task with and false is not true {}. ' +Original acc: 16.88%, attacked acc: 13.75%, dropped acc: 3.12% + +Original prompt: Solve the following math question about {}. +Attacked prompt: b'Solve the following math question about and false is not true {}. ' +Original acc: 16.25%, attacked acc: 12.50%, dropped acc: 3.75% + +Original prompt: Calculate the answer to the following math query about {}. +Attacked prompt: b'Calculate the answer to the following math query about and false is not true {}. ' +Original acc: 16.25%, attacked acc: 13.75%, dropped acc: 2.50% + +Original prompt: Pretend you are a math teacher and solve this mathematical question concerning {}. +Attacked prompt: b'Pretend you are a math teacher and solve this mathematical question concerning and false is not true {}. ' +Original acc: 16.88%, attacked acc: 12.50%, dropped acc: 4.38% + +Original prompt: Act as a math expert and compute the result of the following mathematical task about {}. +Attacked prompt: b'Act as a math expert and compute the result of the following mathematical task about and false is not true {}. ' +Original acc: 16.25%, attacked acc: 12.50%, dropped acc: 3.75% + +Original prompt: As a mathematics consultant, resolve the following problem associated with {}. +Attacked prompt: b'As a mathematics consultant, resolve the following problem associated with and false is not true {}. ' +Original acc: 16.25%, attacked acc: 13.12%, dropped acc: 3.12% + +## textbugger + +Original prompt: Figure out the solution for the following mathematical task with {}. +Attacked prompt: b'Figure out the solution for the followin\xc9\xa1 mathematical task with {}. ' +Original acc: 16.88%, attacked acc: 15.00%, dropped acc: 1.88% + +Original prompt: Solve the following math question about {}. +Attacked prompt: b'Sovle the following math question about {}. ' +Original acc: 16.25%, attacked acc: 15.00%, dropped acc: 1.25% + +Original prompt: Calculate the answer to the following math query about {}. +Attacked prompt: b'Calculate the replying to the following math query about {}. ' +Original acc: 16.25%, attacked acc: 15.62%, dropped acc: 0.63% + +Original prompt: Pretend you are a math teacher and solve this mathematical question concerning {}. +Attacked prompt: b'Pretend you are a math teacher and settle this matehmatical question on {}. ' +Original acc: 16.88%, attacked acc: 13.75%, dropped acc: 3.12% + +Original prompt: Act as a math expert and compute the result of the following mathematical task about {}. +Attacked prompt: b'Act as a math expret and compute the result of the following mathematical task about {}. ' +Original acc: 16.25%, attacked acc: 15.00%, dropped acc: 1.25% + +Original prompt: As a mathematics consultant, resolve the following problem associated with {}. +Attacked prompt: b'As a math consultant, resolve the following poblem associated with {}. ' +Original acc: 16.25%, attacked acc: 14.37%, dropped acc: 1.88% + +## textfooler + +Original prompt: Figure out the solution for the following mathematical task with {}. +Attacked prompt: b'Figure out the address for the farther arithmetic task with {}. ' +Original acc: 16.88%, attacked acc: 14.37%, dropped acc: 2.50% + +Original prompt: Solve the following math question about {}. +Attacked prompt: b'Solve the following math question about {}. ' +Original acc: 16.25%, attacked acc: 16.25%, dropped acc: 0.63% + +Original prompt: Calculate the answer to the following math query about {}. +Attacked prompt: b'Estimate the rebuttal to the following math view about {}. ' +Original acc: 16.25%, attacked acc: 10.00%, dropped acc: 6.25% + +Original prompt: Pretend you are a math teacher and solve this mathematical question concerning {}. +Attacked prompt: b'Pretend you are a math teacher and fix this mathematical question concerning {}. ' +Original acc: 16.88%, attacked acc: 15.00%, dropped acc: 1.88%Original prompt: Act as a math expert and compute the result of the following mathematical task about {}. +Attacked prompt: b'Act as a math expert and estimate the conclusion of the following mathematical task about {}. ' +Original acc: 16.25%, attacked acc: 13.75%, dropped acc: 2.50% + +Original prompt: As a mathematics consultant, resolve the following problem associated with {}. +Attacked prompt: b'As a math consultant, resolve the following difficulty associated with {}. ' +Original acc: 16.25%, attacked acc: 13.75%, dropped acc: 2.50% + +## translation + +Language: chinese, acc: 13.75%, prompt: Calculate the answer to a mathematical question about {}. +Language: chinese, acc: 10.62%, prompt: Calculate the value of {}. +Language: chinese, acc: 12.50%, prompt: Please calculate the result of {}. +Language: chinese, acc: 14.37%, prompt: According to {}, solve the following mathematical problem. +Language: chinese, acc: 11.88%, prompt: Do the math with {}. +Language: chinese, acc: 13.75%, prompt: Solve mathematical problems involving {}. +Language: chinese, acc: 13.12%, prompt: Please calculate the answer involving {}. +Language: chinese, acc: 13.12%, prompt: Solve for the following values based on {}. +Language: chinese, acc: 13.75%, prompt: Calculate the following mathematical tasks using {}. +Language: chinese, acc: 12.50%, prompt: Calculate the answer to the {} related question. +Language: french, acc: 13.75%, prompt: Calculate the answer to the following mathematical question concerning {}. +Language: french, acc: 12.50%, prompt: Calculate the result of {}. +Language: french, acc: 10.62%, prompt: Please calculate the value of {}. +Language: french, acc: 14.37%, prompt: According to {}, solve the following mathematical problem. +Language: french, acc: 14.37%, prompt: Perform mathematical calculations with {}. +Language: french, acc: 14.37%, prompt: Solve the mathematical problem involving {}. +Language: french, acc: 12.50%, prompt: Please calculate the answer related to {}. +Language: french, acc: 10.00%, prompt: According to {}, set the following value. +Language: french, acc: 11.88%, prompt: Perform the following mathematical task using {}. +Language: french, acc: 13.75%, prompt: Calculate the answer to the questions related to {}. +Language: arabic, acc: 14.37%, prompt: Compute the answer to the next mathematical question about {}. +Language: arabic, acc: 13.75%, prompt: Calculate {}. +Language: arabic, acc: 13.75%, prompt: Please calculate {}. +Language: arabic, acc: 14.37%, prompt: According to {}, solve the following mathematical problem. +Language: arabic, acc: 11.88%, prompt: Do mathematical calculations using {}. +Language: arabic, acc: 14.37%, prompt: A solution to the mathematical problem involving {}. +Language: arabic, acc: 11.88%, prompt: Please calculate the answer regarding {}. +Language: arabic, acc: 13.12%, prompt: According to {}, determine the next value. +Language: arabic, acc: 13.12%, prompt: DO THE NEXT MATHEMATICAL JOB USING {}. +Language: arabic, acc: 13.75%, prompt: Calculate the answer to questions related to {}. +Language: spanish, acc: 12.50%, prompt: Compute the answer to the following mathematical question on {}. +Language: spanish, acc: 12.50%, prompt: Compute the result of {}. +Language: spanish, acc: 10.62%, prompt: Please calculate the value of {}. +Language: spanish, acc: 13.12%, prompt: As {}, it solves the following mathematical problem. +Language: spanish, acc: 14.37%, prompt: Performs mathematical calculations using {}. +Language: spanish, acc: 14.37%, prompt: Solve the mathematical problem involving {}. +Language: spanish, acc: 12.50%, prompt: Please calculate the answer related to {}. +Language: spanish, acc: 12.50%, prompt: As {}, determine the next value. +Language: spanish, acc: 11.88%, prompt: Perform the following mathematical task using {}. +Language: spanish, acc: 14.37%, prompt: Compute the answer to questions related to {}. +Language: japanese, acc: 14.37%, prompt: Calculate the answers to the math questions about {}. +Language: japanese, acc: 10.62%, prompt: Calculate the value of {}. +Language: japanese, acc: 12.50%, prompt: Please find the answer to {}. +Language: japanese, acc: 15.62%, prompt: Based on {}, please solve the following mathematical problems. +Language: japanese, acc: 15.00%, prompt: Use {} to perform mathematical calculations. +Language: japanese, acc: 13.12%, prompt: Please solve the math problem that contains {}. +Language: japanese, acc: 13.12%, prompt: Please calculate the answers related to {}. +Language: japanese, acc: 15.62%, prompt: Based on {}, find the following values: +Language: japanese, acc: 13.75%, prompt: Use {} to solve the following mathematical problem. +Language: japanese, acc: 13.75%, prompt: Please calculate the answers to the questions related to {}. +Language: korean, acc: 13.75%, prompt: Calculate the answer of the following math problem to {}. +Language: korean, acc: 12.50%, prompt: Calculate the result of {}. +Language: korean, acc: 10.62%, prompt: Please calculate the value of {}. +Language: korean, acc: 13.12%, prompt: Work out the following math problems according to {}. +Language: korean, acc: 14.37%, prompt: Use {} to proceed with mathematical calculations. +Language: korean, acc: 13.75%, prompt: Work out a math problem involving {}. +Language: korean, acc: 11.88%, prompt: Please calculate the answer to {}. +Language: korean, acc: 11.25%, prompt: Try to get the following values according to {}. +Language: korean, acc: 11.25%, prompt: Work out the next math task using {}. +Language: korean, acc: 13.12%, prompt: Calculate the answer of the problem involving {}. \ No newline at end of file