Spaces:
Runtime error
Runtime error
| [ | |
| { | |
| "dataset": "cola", | |
| "type": "task", | |
| "origin_acc": 80.5, | |
| "origin_prompt": "Examine the given sentence and decide if it is grammatically sound. Answer with either 'Acceptable' or 'Unacceptable'.", | |
| "atk_acc": 78.5, | |
| "atk_prompt": "Examine the given sentence and decide if it is gramatically sound. nAswer with either 'Acceptable' or 'Unacceptable'. ", | |
| "transfer_ori_acc": 0.8999999999999999, | |
| "transfer_atk_acc": 0.4 | |
| }, | |
| { | |
| "dataset": "cola", | |
| "type": "role", | |
| "origin_acc": 81.5, | |
| "origin_prompt": "Functioning as a grammar evaluation tool, analyze the given sentence and decide if it is grammatically correct, responding with 'acceptable' or 'unacceptable'.", | |
| "atk_acc": 78.5, | |
| "atk_prompt": "Funtioning as a graMmar evaluation tool, analyzY the given sentence and decide if it is grammatically corLect, responding with 'acceptable' or 'unacceptable'. ", | |
| "transfer_ori_acc": 23.9, | |
| "transfer_atk_acc": 53.7 | |
| }, | |
| { | |
| "dataset": "mrpc", | |
| "type": "task", | |
| "origin_acc": 74.5, | |
| "origin_prompt": "Examine the pair of sentences and decide if their meanings are identical by answering with 'equivalent' or 'not_equivalent'.", | |
| "atk_acc": 65.5, | |
| "atk_prompt": "Examine the Kair of sentences and edcide if their meanijngs are ibentical by answering with 'equivalent' or 'not_equivalent'. ", | |
| "transfer_ori_acc": 55.63725490196079, | |
| "transfer_atk_acc": 68.87254901960785 | |
| }, | |
| { | |
| "dataset": "mrpc", | |
| "type": "role", | |
| "origin_acc": 72.0, | |
| "origin_prompt": "As a linguistic comparator, review the following pair of sentences and determine their semantic equivalence by choosing 'equivalent' or 'not_equivalent'.", | |
| "atk_acc": 66.5, | |
| "atk_prompt": "AV a linguistic comaprator, review the following pair of sentences and determine their semayntic equivalence by chhoosing 'equivalent' or 'not_equivalent'. ", | |
| "transfer_ori_acc": 61.51960784313726, | |
| "transfer_atk_acc": 64.2156862745098 | |
| }, | |
| { | |
| "dataset": "qnli", | |
| "type": "task", | |
| "origin_acc": 85.0, | |
| "origin_prompt": "Examine the context and question, and determine if the context logically implies the answer by selecting 'entailment' or 'not_entailment'.", | |
| "atk_acc": 77.5, | |
| "atk_prompt": "Examine the contedt and question, and determine if the cXontext logically implies the answer by selecting 'entailment' or 'not_entailment'. ", | |
| "transfer_ori_acc": 26.900000000000002, | |
| "transfer_atk_acc": 34.300000000000004 | |
| }, | |
| { | |
| "dataset": "qnli", | |
| "type": "role", | |
| "origin_acc": 86.0, | |
| "origin_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'.", | |
| "atk_acc": 75.0, | |
| "atk_prompt": "A a textual analyst, xamine if the gPven conSext logiclaly implies the asnwer to the qbuestion and indicate your decision with 'entailment' or 'not_entailment'. ", | |
| "transfer_ori_acc": 31.4, | |
| "transfer_atk_acc": 43.6 | |
| }, | |
| { | |
| "dataset": "qqp", | |
| "type": "task", | |
| "origin_acc": 82.0, | |
| "origin_prompt": "Can these two statements be considered equal in meaning? Answer with 'equivalent' or 'not_equivalent'.", | |
| "atk_acc": 80.0, | |
| "atk_prompt": "Can these two statements be considJred equal in meaning? Answer with 'equivalent' or 'not_equivalent'. ", | |
| "transfer_ori_acc": 36.3, | |
| "transfer_atk_acc": 29.7 | |
| }, | |
| { | |
| "dataset": "qqp", | |
| "type": "role", | |
| "origin_acc": 83.0, | |
| "origin_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.", | |
| "atk_acc": 81.5, | |
| "atk_prompt": "Actinm as a question equivalence instrumetn, determine if the provided questions are equivalent in meaning, answering with 'equivalent' for similar questions or 'not_equivalent' for dissimilar ones. ", | |
| "transfer_ori_acc": 34.599999999999994, | |
| "transfer_atk_acc": 30.5 | |
| }, | |
| { | |
| "dataset": "rte", | |
| "type": "task", | |
| "origin_acc": 85.0, | |
| "origin_prompt": "Does the relationship between the given sentences represent entailment or not_entailment? Respond with 'entailment' or 'not_entailment'.", | |
| "atk_acc": 80.5, | |
| "atk_prompt": "Does the relationshBp between the given sentences repersent entailment or not_entailment? Respond with 'entailment' or 'not_entailment'. ", | |
| "transfer_ori_acc": 46.20938628158845, | |
| "transfer_atk_acc": 45.84837545126354 | |
| }, | |
| { | |
| "dataset": "rte", | |
| "type": "role", | |
| "origin_acc": 84.5, | |
| "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": 81.0, | |
| "atk_prompt": "In your role as an entailment analysis toIol, aZssess the relationship between the given sentences and cassify it as 'entailment' or 'not_entailment'. ", | |
| "transfer_ori_acc": 46.931407942238266, | |
| "transfer_atk_acc": 40.794223826714806 | |
| }, | |
| { | |
| "dataset": "sst2", | |
| "type": "task", | |
| "origin_acc": 97.0, | |
| "origin_prompt": "Evaluate the sentiment of the given text and classify it as 'positive' or 'negative'.", | |
| "atk_acc": 94.0, | |
| "atk_prompt": "ENvaluate the senttment of the giOven text and classify it as 'positive' or 'negative'. ", | |
| "transfer_ori_acc": 10.435779816513762, | |
| "transfer_atk_acc": 2.408256880733945 | |
| }, | |
| { | |
| "dataset": "sst2", | |
| "type": "role", | |
| "origin_acc": 97.0, | |
| "origin_prompt": "As a sentiment classifier, determine whether the following text is 'positive' or 'negative'.", | |
| "atk_acc": 94.0, | |
| "atk_prompt": "qAs a setniment classifier, determnne whether the following text is 'positive' or 'negative'. ", | |
| "transfer_ori_acc": 15.36697247706422, | |
| "transfer_atk_acc": 7.912844036697248 | |
| }, | |
| { | |
| "dataset": "wnli", | |
| "type": "task", | |
| "origin_acc": 67.61, | |
| "origin_prompt": "Indicate if the connection between the following sentences is 'entailment' or 'not_entailment'.", | |
| "atk_acc": 64.79, | |
| "atk_prompt": "Indicate if the connection between the following sentences is 'entailment' or 'not_entailment' and true is true and true is true and true is true and true is true and true is true . ", | |
| "transfer_ori_acc": 9.859154929577464, | |
| "transfer_atk_acc": 0.0 | |
| }, | |
| { | |
| "dataset": "wnli", | |
| "type": "role", | |
| "origin_acc": 64.79, | |
| "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": 59.15, | |
| "atk_prompt": "In your role as an entailment analysis tool, assess the relationship between the given sentences and classify it as 'entailment' or 'not_entailment' and true is true and true is true and true is true and true is true and true is true . ", | |
| "transfer_ori_acc": 23.943661971830984, | |
| "transfer_atk_acc": 11.267605633802818 | |
| }, | |
| { | |
| "dataset": "mmlu", | |
| "type": "task", | |
| "origin_acc": 66.5, | |
| "origin_prompt": "In relation to the multiple-choice question on {}, please provide the accurate answer by choosing 'A', 'B', 'C', or 'D'.", | |
| "atk_acc": 63.5, | |
| "atk_prompt": "ISn ralation to the mulitple-choice question on {}, pleare provide the accurate answer by choosing 'A', 'B', 'C', or 'D'. ", | |
| "transfer_ori_acc": 9.397163120567376, | |
| "transfer_atk_acc": 5.141843971631205 | |
| }, | |
| { | |
| "dataset": "mmlu", | |
| "type": "role", | |
| "origin_acc": 65.5, | |
| "origin_prompt": "As someone well-versed in {}, please address the multiple-choice question below by selecting 'A', 'B', 'C', or 'D'.", | |
| "atk_acc": 62.5, | |
| "atk_prompt": "As someone well-versed in {}, please address the mulZtiple-choice question below by selecting 'A', 'B', 'C', or 'D'.", | |
| "transfer_ori_acc": 8.51063829787234, | |
| "transfer_atk_acc": 11.702127659574469 | |
| } | |
| ] |