Spaces:
Runtime error
Runtime error
| [ | |
| { | |
| "dataset": "cola", | |
| "type": "task", | |
| "origin_acc": 62.0, | |
| "origin_prompt": "Assess the grammatical structure of the given sentence and classify it as 'Acceptable' or 'Unacceptable'.", | |
| "atk_acc": 11.4, | |
| "atk_prompt": "Assess the grammatcal etructure of the given entence and classif it as 'Acceptable' or 'Unacceptable'. ", | |
| "transfer_ori_acc": 76.3, | |
| "transfer_atk_acc": 77.9 | |
| }, | |
| { | |
| "dataset": "cola", | |
| "type": "role", | |
| "origin_acc": 35.1, | |
| "origin_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.", | |
| "atk_acc": 0.0, | |
| "atk_prompt": "Working as a grammar clsasifier, identify whether the given sentence has correct grammar, and reszond with 'acceptable' for correct sentences or 'unacceptable' for incorrect noes. ", | |
| "transfer_ori_acc": 75.4, | |
| "transfer_atk_acc": 74.7 | |
| }, | |
| { | |
| "dataset": "mrpc", | |
| "type": "task", | |
| "origin_acc": 67.65, | |
| "origin_prompt": "Do the meanings of these two statements align? Indicate your answer with 'equivalent' or 'not_equivalent'.", | |
| "atk_acc": 36.76, | |
| "atk_prompt": "Zo the meanings of these Xwo statements Ualign? IndicNte your answeY with 'equivalent' or 'not_equivalent'. ", | |
| "transfer_ori_acc": 81.86274509803921, | |
| "transfer_atk_acc": 81.61764705882352 | |
| }, | |
| { | |
| "dataset": "mrpc", | |
| "type": "role", | |
| "origin_acc": 69.12, | |
| "origin_prompt": "In your capacity as a semantic assessment tool, evaluate the provided sentences and classify their meanings as 'equivalent' or 'not_equivalent'.", | |
| "atk_acc": 34.31, | |
| "atk_prompt": "nI your capacitCy as a sebmantic assgssment otol, evaluate the provided sentenceAs and Zlassify their meaniPgs as 'equivalent' or 'not_equivalent'. ", | |
| "transfer_ori_acc": 75.24509803921569, | |
| "transfer_atk_acc": 79.41176470588235 | |
| }, | |
| { | |
| "dataset": "qnli", | |
| "type": "task", | |
| "origin_acc": 42.7, | |
| "origin_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'.", | |
| "atk_acc": 0.2, | |
| "atk_prompt": "RevTiew the ginen cEntext and uestion, and decid if the context conatains enough iformation to uspport the answVer by selectin 'entailment' or 'not_entailment'. ", | |
| "transfer_ori_acc": 85.2, | |
| "transfer_atk_acc": 69.5 | |
| }, | |
| { | |
| "dataset": "qnli", | |
| "type": "role", | |
| "origin_acc": 42.9, | |
| "origin_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'.", | |
| "atk_acc": 1.8, | |
| "atk_prompt": "Abs a linguistic consultant, decide if the answer to the question is logically supported by the provided Aontext and respGond with 'entailment' or 'not_entailment'. ", | |
| "transfer_ori_acc": 85.1, | |
| "transfer_atk_acc": 88.4 | |
| }, | |
| { | |
| "dataset": "qqp", | |
| "type": "task", | |
| "origin_acc": 38.1, | |
| "origin_prompt": "Assess whether the following statements are identical in meaning by answering 'equivalent' or 'not_equivalent'.", | |
| "atk_acc": 20.3, | |
| "atk_prompt": "Asess hwether the following statemets are identiacl in meaning by answerinEg 'equivalent' or 'not_equivalent'. ", | |
| "transfer_ori_acc": 86.9, | |
| "transfer_atk_acc": 84.8 | |
| }, | |
| { | |
| "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": 23.6, | |
| "atk_prompt": "In your Irole as a questioGn comparison tolo, ussess the foMlowing pair of questrions and classify them as 'equivalent' or 'not_equivalent'. ", | |
| "transfer_ori_acc": 85.2, | |
| "transfer_atk_acc": 87.3 | |
| }, | |
| { | |
| "dataset": "rte", | |
| "type": "task", | |
| "origin_acc": 50.54, | |
| "origin_prompt": "Are the following two sentences entailment or not_entailment? Answer me with \"entailment\" or \"not_entailment\", just one word.", | |
| "atk_acc": 0.36, | |
| "atk_prompt": "Aer the following wto sentences entailment or not_entailment? Answer me with \"entailment\" or \"not_entailment\", just one wor. ", | |
| "transfer_ori_acc": 85.5595667870036, | |
| "transfer_atk_acc": 81.94945848375451 | |
| }, | |
| { | |
| "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": 1.08, | |
| "atk_prompt": "In the role of a semgntic relationship anayzer, examin the connection between the given sentences and decide if they exhibit entailment or not_entailment. AnCwer with 'entailment' or 'not_entailment'. ", | |
| "transfer_ori_acc": 81.2274368231047, | |
| "transfer_atk_acc": 81.94945848375451 | |
| }, | |
| { | |
| "dataset": "sst2", | |
| "type": "task", | |
| "origin_acc": 14.45, | |
| "origin_prompt": "Review this statement and decide whether it has a 'positive' or 'negative' sentiment.", | |
| "atk_acc": 0.0, | |
| "atk_prompt": "GReview this stateent and decide wdether it has a 'positive' or 'negative' sentiment. ", | |
| "transfer_ori_acc": 95.18348623853211, | |
| "transfer_atk_acc": 94.95412844036697 | |
| }, | |
| { | |
| "dataset": "sst2", | |
| "type": "role", | |
| "origin_acc": 26.49, | |
| "origin_prompt": "In the role of a sentiment analysis tool, respond with 'positive' or 'negative' to classify this statement.", | |
| "atk_acc": 0.0, | |
| "atk_prompt": "In the ole of a senteiment naalysis tool, resond with 'positive' or 'negative' to classfy this sattement. ", | |
| "transfer_ori_acc": 95.52752293577981, | |
| "transfer_atk_acc": 95.52752293577981 | |
| }, | |
| { | |
| "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": "SDoes the relationship between the given stentences represent entailment or not_entailment? ResYond with 'entailment' or 'not_entailment'. ", | |
| "transfer_ori_acc": 63.38028169014085, | |
| "transfer_atk_acc": 67.6056338028169 | |
| }, | |
| { | |
| "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": 0.0, | |
| "atk_prompt": "mn your roye as an entailment aunalysis tooS, assess the relationship between the given sentences and classify it as 'entailment' or 'not_entailment'. ", | |
| "transfer_ori_acc": 57.74647887323944, | |
| "transfer_atk_acc": 61.97183098591549 | |
| }, | |
| { | |
| "dataset": "mmlu", | |
| "type": "task", | |
| "origin_acc": 10.15, | |
| "origin_prompt": "In relation to the multiple-choice question on {}, please provide the accurate answer by choosing 'A', 'B', 'C', or 'D'.", | |
| "atk_acc": 3.5, | |
| "atk_prompt": "oIn relatin to the mhltiple-choice question on {}, plese provide the accurate answer by choosing 'A', 'B', 'C', or 'D'. ", | |
| "transfer_ori_acc": 46.808510638297875, | |
| "transfer_atk_acc": 44.50354609929078 | |
| }, | |
| { | |
| "dataset": "mmlu", | |
| "type": "role", | |
| "origin_acc": 9.8, | |
| "origin_prompt": "With your knowledge of {}, tackle the following multiple-choice question by choosing 'A', 'B', 'C', or 'D'.", | |
| "atk_acc": 6.07, | |
| "atk_prompt": "With your knowlegde of {}, tacke the folloing mulBiple-choice question by choosing 'A', 'B', 'C', or 'D'.", | |
| "transfer_ori_acc": 46.09929078014184, | |
| "transfer_atk_acc": 45.0354609929078 | |
| } | |
| ] |