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": 77.7, | |
| "transfer_atk_acc": 77.8 | |
| }, | |
| { | |
| "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": 75.2, | |
| "transfer_atk_acc": 75.8 | |
| }, | |
| { | |
| "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": 82.84313725490196, | |
| "transfer_atk_acc": 79.90196078431373 | |
| }, | |
| { | |
| "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": 79.90196078431373, | |
| "transfer_atk_acc": 79.16666666666666 | |
| }, | |
| { | |
| "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": 86.5, | |
| "transfer_atk_acc": 87.7 | |
| }, | |
| { | |
| "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": 88.8, | |
| "transfer_atk_acc": 80.10000000000001 | |
| }, | |
| { | |
| "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": 87.6, | |
| "transfer_atk_acc": 87.9 | |
| }, | |
| { | |
| "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": 86.5, | |
| "transfer_atk_acc": 85.6 | |
| }, | |
| { | |
| "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": 83.75451263537906, | |
| "transfer_atk_acc": 82.67148014440433 | |
| }, | |
| { | |
| "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": 83.03249097472924, | |
| "transfer_atk_acc": 82.31046931407943 | |
| }, | |
| { | |
| "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": 94.61009174311926, | |
| "transfer_atk_acc": 95.29816513761467 | |
| }, | |
| { | |
| "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": 94.4954128440367, | |
| "transfer_atk_acc": 95.29816513761467 | |
| }, | |
| { | |
| "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": 64.7887323943662, | |
| "transfer_atk_acc": 38.028169014084504 | |
| }, | |
| { | |
| "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": 57.74647887323944, | |
| "transfer_atk_acc": 46.478873239436616 | |
| }, | |
| { | |
| "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": 46.808510638297875, | |
| "transfer_atk_acc": 45.39007092198582 | |
| }, | |
| { | |
| "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": 46.63120567375886, | |
| "transfer_atk_acc": 45.744680851063826 | |
| }, | |
| { | |
| "dataset": "squad_v2", | |
| "type": "task", | |
| "origin_acc": 73.25, | |
| "origin_prompt": "Based on the given context, provide the best possible answer. If there's no answer available in the context, reply with 'unanswerable'.", | |
| "atk_acc": 67.18, | |
| "atk_prompt": "Based on the goiven context, provide the best possible answer. IL there's no answer available in the coYtext, reply with 'unanswerable'.", | |
| "transfer_ori_acc": 87.04992770387507, | |
| "transfer_atk_acc": 87.54992770387507 | |
| }, | |
| { | |
| "dataset": "squad_v2", | |
| "type": "role", | |
| "origin_acc": 72.68, | |
| "origin_prompt": "As a subject matter expert, extract the correct answer from the context. If an answer is not present, indicate 'unanswerable'.", | |
| "atk_acc": 66.77, | |
| "atk_prompt": "s a subject matter eAxpert, extract the correc answer from the context. If an answer is not presnt, idicate 'unanswerable'.", | |
| "transfer_ori_acc": 87.04992770387507, | |
| "transfer_atk_acc": 87.14992770387508 | |
| }, | |
| { | |
| "dataset": "iwslt", | |
| "type": "task", | |
| "origin_acc": 0.23, | |
| "origin_prompt": "Given the sentence below, perform a machine translation from {} to {}.", | |
| "atk_acc": 0.23, | |
| "atk_prompt": "Given the sentence below, perform a mRachine traCslation from {} to {}. ", | |
| "transfer_ori_acc": 0.21292285800980326, | |
| "transfer_atk_acc": 0.21552262845169096 | |
| }, | |
| { | |
| "dataset": "iwslt", | |
| "type": "role", | |
| "origin_acc": 0.24, | |
| "origin_prompt": "Assuming the responsibilities of a professional translator, translate the subsequent text passage from {} to {}.", | |
| "atk_acc": 0.23, | |
| "atk_prompt": "Assuming the responsibilities of a professional transaltor, translate the subsequent text passage from {} to {}. ", | |
| "transfer_ori_acc": 0.22030199520456395, | |
| "transfer_atk_acc": 0.21973314066426236 | |
| }, | |
| { | |
| "dataset": "un_multi", | |
| "type": "task", | |
| "origin_acc": 0.35, | |
| "origin_prompt": "Please perform a translation of the given sentence, converting it from {} to {}.", | |
| "atk_acc": 0.26, | |
| "atk_prompt": "Plese erform a translation of the Fiven sentence, converwing it from {} to {}. ", | |
| "transfer_ori_acc": 0.3076276888167265, | |
| "transfer_atk_acc": 0.3054838402284908 | |
| }, | |
| { | |
| "dataset": "un_multi", | |
| "type": "role", | |
| "origin_acc": 0.35, | |
| "origin_prompt": "As a qualified translator, convert the given sentence from its original {} language to the target language {}.", | |
| "atk_acc": 0.35, | |
| "atk_prompt": "As a qualified translator, convert the given sentence from its original {} language to the targte language {}. ", | |
| "transfer_ori_acc": 0.31127691224033316, | |
| "transfer_atk_acc": 0.3078172023513576 | |
| }, | |
| { | |
| "dataset": "math", | |
| "type": "task", | |
| "origin_acc": 23.12, | |
| "origin_prompt": "Calculate the answer to the following math query about {}.", | |
| "atk_acc": 18.75, | |
| "atk_prompt": "Calculate the ansewr to the followiJg math query about {}. ", | |
| "transfer_ori_acc": 16.25, | |
| "transfer_atk_acc": 16.25 | |
| }, | |
| { | |
| "dataset": "math", | |
| "type": "role", | |
| "origin_acc": 23.12, | |
| "origin_prompt": "As a mathematics instructor, calculate the answer to the following problem related to {}.", | |
| "atk_acc": 20.62, | |
| "atk_prompt": "As a mathematics insrtuctor, calculate the answer to the following problem Vrelated to {}. ", | |
| "transfer_ori_acc": 17.5, | |
| "transfer_atk_acc": 16.25 | |
| } | |
| ] |