Spaces:
Runtime error
Runtime error
| [ | |
| { | |
| "dataset": "cola", | |
| "type": "task", | |
| "origin_acc": 62.2, | |
| "origin_prompt": "Assess the grammatical structure of the given sentence and classify it as 'Acceptable' or 'Unacceptable'.", | |
| "atk_acc": 2.2, | |
| "atk_prompt": "Assess the grammatically s𝚝ructure of the ɡiven sentecne and clasisfy it as 'Acceptable' or 'Unacceptable'. ", | |
| "transfer_ori_acc": 79.5, | |
| "transfer_atk_acc": 79.0 | |
| }, | |
| { | |
| "dataset": "cola", | |
| "type": "role", | |
| "origin_acc": 48.0, | |
| "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": 0.0, | |
| "atk_prompt": "Whie peⲅforming grammar analysis, ϲlassify the grammatical of the following sentence as 'acceptable' for correct grammar or 'unacceptable' for incorrect grammr. ", | |
| "transfer_ori_acc": 82.0, | |
| "transfer_atk_acc": 81.0 | |
| }, | |
| { | |
| "dataset": "mrpc", | |
| "type": "task", | |
| "origin_acc": 68.38, | |
| "origin_prompt": "Assess if the two given sentences have equivalent meanings by selecting 'equivalent' or 'not_equivalent'.", | |
| "atk_acc": 44.61, | |
| "atk_prompt": "Assessing if the t wo given sentences have equivalent meanings by selectiոg 'equivalent' or 'not_equivalent'. ", | |
| "transfer_ori_acc": 71.5, | |
| "transfer_atk_acc": 70.0 | |
| }, | |
| { | |
| "dataset": "mrpc", | |
| "type": "role", | |
| "origin_acc": 68.14, | |
| "origin_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'.", | |
| "atk_acc": 44.36, | |
| "atk_prompt": "Onto the role of a senteոce c omparison analys𝚝, assess the given sentences and indicate if they convey the same meaning by selecting 'equivalent' or 'not_equivalent'. ", | |
| "transfer_ori_acc": 70.5, | |
| "transfer_atk_acc": 69.0 | |
| }, | |
| { | |
| "dataset": "qnli", | |
| "type": "task", | |
| "origin_acc": 38.9, | |
| "origin_prompt": "Analyze the context and question, and indicate if the context entails the answer by choosing 'entailment' or 'not_entailment'.", | |
| "atk_acc": 0.7, | |
| "atk_prompt": "Analyze the context and question, and depicts if the context involves the ans wer by choosiոg 'entailment' or 'not_entailment'. ", | |
| "transfer_ori_acc": 81.0, | |
| "transfer_atk_acc": 81.0 | |
| }, | |
| { | |
| "dataset": "qnli", | |
| "type": "role", | |
| "origin_acc": 41.4, | |
| "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": 0.0, | |
| "atk_prompt": "As a semantic reesarcher, evaluating whether the provided context supports the answering to the question and chosen 'entailment' or 'not_entailment'. ", | |
| "transfer_ori_acc": 82.5, | |
| "transfer_atk_acc": 83.0 | |
| }, | |
| { | |
| "dataset": "qqp", | |
| "type": "task", | |
| "origin_acc": 41.8, | |
| "origin_prompt": "Do the following expressions mean the same thing? Provide your answer as 'equivalent' or 'not_equivalent'.", | |
| "atk_acc": 26.7, | |
| "atk_prompt": "Wo the following expressions meant the same thing? Provide your aոswer as 'equivalent' or 'not_equivalent'. ", | |
| "transfer_ori_acc": 82.5, | |
| "transfer_atk_acc": 83.0 | |
| }, | |
| { | |
| "dataset": "qqp", | |
| "type": "role", | |
| "origin_acc": 33.6, | |
| "origin_prompt": "In your role as a question comparison tool, assess the following pair of questions and classify them as 'equivalent' or 'not_equivalent'.", | |
| "atk_acc": 15.0, | |
| "atk_prompt": "For your roⅼe as a question compɑrison tool, evaluate the 𝚏ollowing pair of questions and categorized them as 'equivalent' or 'not_equivalent'. ", | |
| "transfer_ori_acc": 81.0, | |
| "transfer_atk_acc": 83.0 | |
| }, | |
| { | |
| "dataset": "rte", | |
| "type": "task", | |
| "origin_acc": 43.68, | |
| "origin_prompt": "Review the two statements and categorize their relationship as either 'entailment' or 'not_entailment'.", | |
| "atk_acc": 2.53, | |
| "atk_prompt": "Revіew the two sta𝚝ements and categorize their relationship as or 'entailment' or 'not_entailment'. ", | |
| "transfer_ori_acc": 82.5, | |
| "transfer_atk_acc": 84.0 | |
| }, | |
| { | |
| "dataset": "rte", | |
| "type": "role", | |
| "origin_acc": 36.82, | |
| "origin_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'.", | |
| "atk_acc": 0.0, | |
| "atk_prompt": "In the role of a seｍantic relationship analyzeⲅ, examine the connection between the givn sentences and determine if they exhibi𝚝 entailment or not_entailment. Answers with 'entailment' or 'not_entailment'. ", | |
| "transfer_ori_acc": 82.5, | |
| "transfer_atk_acc": 83.5 | |
| }, | |
| { | |
| "dataset": "sst2", | |
| "type": "task", | |
| "origin_acc": 18.12, | |
| "origin_prompt": "Evaluate the sentiment of the given text and classify it as 'positive' or 'negative'.", | |
| "atk_acc": 0.0, | |
| "atk_prompt": "Evaluate the vibe of the gievn text and calssify it as 'positive' or 'negative'. ", | |
| "transfer_ori_acc": 95.5, | |
| "transfer_atk_acc": 92.5 | |
| }, | |
| { | |
| "dataset": "sst2", | |
| "type": "role", | |
| "origin_acc": 33.37, | |
| "origin_prompt": "Taking on the role of an emotion classifier, specify if the provided phrase is 'positive' or 'negative'.", | |
| "atk_acc": 0.57, | |
| "atk_prompt": "Taking on the roles of an emotions classi𝚏ier, speci𝚏y if the povided phrase is 'positive' or 'negative'. ", | |
| "transfer_ori_acc": 94.5, | |
| "transfer_atk_acc": 93.0 | |
| }, | |
| { | |
| "dataset": "wnli", | |
| "type": "task", | |
| "origin_acc": 23.94, | |
| "origin_prompt": "Does the relationship between the given sentences represent entailment or not_entailment? Respond with 'entailment' or 'not_entailment'.", | |
| "atk_acc": 0.0, | |
| "atk_prompt": "Does the relations between the given sentences ⲅepresent entailment or not_entailment? Respоnd with 'entailment' or 'not_entailment'. ", | |
| "transfer_ori_acc": 67.6056338028169, | |
| "transfer_atk_acc": 74.64788732394366 | |
| }, | |
| { | |
| "dataset": "wnli", | |
| "type": "role", | |
| "origin_acc": 16.9, | |
| "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": 1.41, | |
| "atk_prompt": "During your role as an entailment aalysis tool, assess the relationshiр between the given sentences and classify it as 'entailment' or 'not_entailment'. ", | |
| "transfer_ori_acc": 61.97183098591549, | |
| "transfer_atk_acc": 61.97183098591549 | |
| }, | |
| { | |
| "dataset": "mmlu", | |
| "type": "task", | |
| "origin_acc": 9.1, | |
| "origin_prompt": "Answer the subsequent multiple-choice question about {} by picking the right option among 'A', 'B', 'C', or 'D'.", | |
| "atk_acc": 3.5, | |
| "atk_prompt": "Responding the subequent multipl-echoice question about {} by pick the right op𝚝ion amongst 'A', 'B', 'C', or 'D'. ", | |
| "transfer_ori_acc": 66.5, | |
| "transfer_atk_acc": 66.0 | |
| }, | |
| { | |
| "dataset": "mmlu", | |
| "type": "role", | |
| "origin_acc": 9.68, | |
| "origin_prompt": "With your understanding of {}, kindly answer the subsequent multiple-choice question by selecting 'A', 'B', 'C', or 'D'.", | |
| "atk_acc": 2.45, | |
| "atk_prompt": "Witհ your understand of {}, 𝒌indly answer the successive mսltiple-choice question by selecting 'A', 'B', 'C', or 'D'.", | |
| "transfer_ori_acc": 64.0, | |
| "transfer_atk_acc": 65.5 | |
| } | |
| ] |