Spaces:
Runtime error
Runtime error
[ | |
{ | |
"dataset": "cola", | |
"type": "task", | |
"origin_acc": 86.4, | |
"origin_prompt": "Examine the given sentence and decide if it is grammatically sound. Answer with either 'Acceptable' or 'Unacceptable'.", | |
"atk_acc": 39.5, | |
"atk_prompt": "Inspect the made condemning and select if it is grammatically healthier. Answers with either 'Acceptable' or 'Unacceptable'. ", | |
"transfer_ori_acc": 0.8999999999999999, | |
"transfer_atk_acc": 5.800000000000001 | |
}, | |
{ | |
"dataset": "cola", | |
"type": "role", | |
"origin_acc": 86.6, | |
"origin_prompt": "While performing grammar analysis, classify the grammar of the following sentence as 'acceptable' for correct grammar or 'unacceptable' for incorrect grammar.", | |
"atk_acc": 73.0, | |
"atk_prompt": "While performing grammar scans, classify the verbs of the afterward condemned as 'acceptable' for correctness grammar or 'unacceptable' for inappropriate vocabulary. ", | |
"transfer_ori_acc": 49.9, | |
"transfer_atk_acc": 7.7 | |
}, | |
{ | |
"dataset": "mrpc", | |
"type": "task", | |
"origin_acc": 86.52, | |
"origin_prompt": "Compare the following sentences and determine if they share the same semantic meaning by responding with 'equivalent' or 'not_equivalent'.", | |
"atk_acc": 83.58, | |
"atk_prompt": "Compare the later judgements and defines if they exchange the same semantic sensation by answered with 'equivalent' or 'not_equivalent'. ", | |
"transfer_ori_acc": 62.254901960784316, | |
"transfer_atk_acc": 72.05882352941177 | |
}, | |
{ | |
"dataset": "mrpc", | |
"type": "role", | |
"origin_acc": 89.22, | |
"origin_prompt": "As a sentence similarity evaluator, analyze the provided sentences and indicate if their meanings are 'equivalent' or 'not_equivalent'.", | |
"atk_acc": 85.29, | |
"atk_prompt": "As a sentence metaphor evaluator, analyze the brought priors and demonstrating if their meanings are 'equivalent' or 'not_equivalent'. ", | |
"transfer_ori_acc": 68.13725490196079, | |
"transfer_atk_acc": 70.58823529411765 | |
}, | |
{ | |
"dataset": "qnli", | |
"type": "task", | |
"origin_acc": 94.0, | |
"origin_prompt": "Analyze the context and question, and indicate if the context entails the answer by choosing 'entailment' or 'not_entailment'.", | |
"atk_acc": 54.2, | |
"atk_prompt": "Explore the context and question, and suggest if the context involves the rebuttal by selected 'entailment' or 'not_entailment'. ", | |
"transfer_ori_acc": 35.0, | |
"transfer_atk_acc": 21.0 | |
}, | |
{ | |
"dataset": "qnli", | |
"type": "role", | |
"origin_acc": 93.9, | |
"origin_prompt": "As a semantic researcher, evaluate whether the provided context supports the answer to the question and choose 'entailment' or 'not_entailment'.", | |
"atk_acc": 61.5, | |
"atk_prompt": "Because a semantic inquisitors, appraise whether the provided context alleges the rebuttal to the issuing and selector 'entailment' or 'not_entailment'. ", | |
"transfer_ori_acc": 41.6, | |
"transfer_atk_acc": 36.7 | |
}, | |
{ | |
"dataset": "qqp", | |
"type": "task", | |
"origin_acc": 88.7, | |
"origin_prompt": "Examine the following expressions and tell me if they are alike in meaning by using 'equivalent' or 'not_equivalent'.", | |
"atk_acc": 85.9, | |
"atk_prompt": "Examine the afterward words and saying me if they are uniformly in connotation by using 'equivalent' or 'not_equivalent'. ", | |
"transfer_ori_acc": 44.9, | |
"transfer_atk_acc": 34.0 | |
}, | |
{ | |
"dataset": "qqp", | |
"type": "role", | |
"origin_acc": 90.0, | |
"origin_prompt": "As a tool for determining question equivalence, review the questions and categorize their similarity as either 'equivalent' or 'not_equivalent'.", | |
"atk_acc": 87.6, | |
"atk_prompt": "Because a tool for determining question equivalence, examination the queries and classifications their likeness as either 'equivalent' or 'not_equivalent'. ", | |
"transfer_ori_acc": 31.7, | |
"transfer_atk_acc": 31.2 | |
}, | |
{ | |
"dataset": "rte", | |
"type": "task", | |
"origin_acc": 93.5, | |
"origin_prompt": "Identify whether the given pair of sentences demonstrates entailment or not_entailment. Answer with 'entailment' or 'not_entailment'.", | |
"atk_acc": 92.42, | |
"atk_prompt": "Deciding whether the given pair of sentencing demonstrates entailment or not_entailment. Answer with 'entailment' or 'not_entailment'. ", | |
"transfer_ori_acc": 7.2202166064981945, | |
"transfer_atk_acc": 47.292418772563174 | |
}, | |
{ | |
"dataset": "rte", | |
"type": "role", | |
"origin_acc": 93.5, | |
"origin_prompt": "As a tool for determining entailment relationships, review the two statements and categorize their connection as either 'entailment' or 'not_entailment'.", | |
"atk_acc": 91.34, | |
"atk_prompt": "Because a device for determining entailment relationships, review the two words and categorize their connection as either 'entailment' or 'not_entailment'. ", | |
"transfer_ori_acc": 28.158844765342963, | |
"transfer_atk_acc": 9.025270758122744 | |
}, | |
{ | |
"dataset": "sst2", | |
"type": "task", | |
"origin_acc": 96.79, | |
"origin_prompt": "Determine the overall sentiment of this sentence, categorizing it as 'positive' or 'negative'.", | |
"atk_acc": 93.46, | |
"atk_prompt": "Determine the plenary senses of this condemning, categorizing it as 'positive' or 'negative'. ", | |
"transfer_ori_acc": 0.573394495412844, | |
"transfer_atk_acc": 1.6055045871559634 | |
}, | |
{ | |
"dataset": "sst2", | |
"type": "role", | |
"origin_acc": 96.56, | |
"origin_prompt": "As a sentiment classifier, determine whether the following text is 'positive' or 'negative'.", | |
"atk_acc": 95.18, | |
"atk_prompt": "As a emotion classifier, ascertain whether the suite wording is 'positive' or 'negative'. ", | |
"transfer_ori_acc": 15.36697247706422, | |
"transfer_atk_acc": 18.807339449541285 | |
}, | |
{ | |
"dataset": "wnli", | |
"type": "task", | |
"origin_acc": 77.46, | |
"origin_prompt": "Assess the connection between the following sentences and classify it as 'entailment' or 'not_entailment'.", | |
"atk_acc": 73.24, | |
"atk_prompt": "Appraisal the attach between the suite condemns and classify it as 'entailment' or 'not_entailment'. ", | |
"transfer_ori_acc": 19.718309859154928, | |
"transfer_atk_acc": 7.042253521126761 | |
}, | |
{ | |
"dataset": "wnli", | |
"type": "role", | |
"origin_acc": 76.06, | |
"origin_prompt": "In your role as an entailment analysis tool, assess the relationship between the given sentences and classify it as 'entailment' or 'not_entailment'.", | |
"atk_acc": 73.24, | |
"atk_prompt": "In your role as an entailment analysis tool, assess the reports between the given sentences and classify it as 'entailment' or 'not_entailment'. ", | |
"transfer_ori_acc": 23.943661971830984, | |
"transfer_atk_acc": 23.943661971830984 | |
}, | |
{ | |
"dataset": "mmlu", | |
"type": "task", | |
"origin_acc": 54.08, | |
"origin_prompt": "For the multiple-choice question related to {}, please choose the most accurate answer from 'A', 'B', 'C', or 'D'.", | |
"atk_acc": 24.82, | |
"atk_prompt": "Within the multiple-choice item relevant to {}, please decides the most careful rebuttal from 'A', 'B', 'C', or 'D'. ", | |
"transfer_ori_acc": 7.2695035460992905, | |
"transfer_atk_acc": 6.560283687943262 | |
}, | |
{ | |
"dataset": "mmlu", | |
"type": "role", | |
"origin_acc": 53.72, | |
"origin_prompt": "As an expert in {}, respond to the following multiple-choice question by selecting 'A', 'B', 'C', or 'D'.", | |
"atk_acc": 51.95, | |
"atk_prompt": "As an whiz in {}, respond to the following multiple-choice question by decided 'A', 'B', 'C', or 'D'.", | |
"transfer_ori_acc": 9.042553191489363, | |
"transfer_atk_acc": 10.28368794326241 | |
} | |
] |