Spaces:
Runtime error
Runtime error
| [ | |
| { | |
| "dataset": "cola", | |
| "type": "task", | |
| "origin_acc": 47.7, | |
| "origin_prompt": "Examine the sentence and decide if its grammar is 'Acceptable' or 'Unacceptable'.", | |
| "atk_acc": 8.0, | |
| "atk_prompt": "Discuss the sentencing and choosing if its language is 'Acceptable' or 'Unacceptable'. ", | |
| "transfer_ori_acc": 80.0, | |
| "transfer_atk_acc": 78.5 | |
| }, | |
| { | |
| "dataset": "cola", | |
| "type": "role", | |
| "origin_acc": 35.2, | |
| "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 classifier, identify whether the given sentence has correct jargon, and cope with 'acceptable' for correct punishments or 'unacceptable' for inappropriate ones. ", | |
| "transfer_ori_acc": 80.0, | |
| "transfer_atk_acc": 75.5 | |
| }, | |
| { | |
| "dataset": "mrpc", | |
| "type": "task", | |
| "origin_acc": 69.36, | |
| "origin_prompt": "Determine if the meanings of the following sentences are semantically equivalent by responding with 'equivalent' or 'not_equivalent'.", | |
| "atk_acc": 35.54, | |
| "atk_prompt": "Decide if the senses of the following sentence are semantically equivalent by meet with 'equivalent' or 'not_equivalent'. ", | |
| "transfer_ori_acc": 70.5, | |
| "transfer_atk_acc": 71.5 | |
| }, | |
| { | |
| "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": 13.24, | |
| "atk_prompt": "Towards the feature of a judgements versus psychoanalyst, reviews the supplied sentences and clarified if they convey the same senses by electing 'equivalent' or 'not_equivalent'. ", | |
| "transfer_ori_acc": 71.5, | |
| "transfer_atk_acc": 66.0 | |
| }, | |
| { | |
| "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": 0.0, | |
| "atk_prompt": "Discuss the given context and tura, and decide if the context encompasses enough information to support the satisfy by takes 'entailment' or 'not_entailment'. ", | |
| "transfer_ori_acc": 84.0, | |
| "transfer_atk_acc": 82.5 | |
| }, | |
| { | |
| "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": 0.1, | |
| "atk_prompt": "As a semantic researcher, appraisals whether the provided context supports the answer to the question and taking 'entailment' or 'not_entailment'. ", | |
| "transfer_ori_acc": 82.5, | |
| "transfer_atk_acc": 81.5 | |
| }, | |
| { | |
| "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": 21.5, | |
| "atk_prompt": "Estimates whether the following pronouncements are analogous in connotation by answering 'equivalent' or 'not_equivalent'. ", | |
| "transfer_ori_acc": 81.5, | |
| "transfer_atk_acc": 83.5 | |
| }, | |
| { | |
| "dataset": "qqp", | |
| "type": "role", | |
| "origin_acc": 33.0, | |
| "origin_prompt": "In the role of a question similarity analyzer, examine the meaning of the provided questions and decide if they are equivalent, answering with 'equivalent' for equivalent questions or 'not_equivalent' for different questions.", | |
| "atk_acc": 13.9, | |
| "atk_prompt": "Across the rol of a trouble similarity analyzer, exploring the meaning of the lent questions and select if they are equivalent, answered with 'equivalent' for equivalent theme or 'not_equivalent' for various questions. ", | |
| "transfer_ori_acc": 81.5, | |
| "transfer_atk_acc": 82.5 | |
| }, | |
| { | |
| "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": 2.17, | |
| "atk_prompt": "Investigated the two statements and categorize their relation as either 'entailment' or 'not_entailment'. ", | |
| "transfer_ori_acc": 82.5, | |
| "transfer_atk_acc": 83.0 | |
| }, | |
| { | |
| "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 profiler, review the ties between the given sentences and determining if they fairs entailment or not_entailment. Answers with 'entailment' or 'not_entailment'. ", | |
| "transfer_ori_acc": 83.0, | |
| "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": "Assessment the mood of the made laws and rank it as 'positive' or 'negative'. ", | |
| "transfer_ori_acc": 96.0, | |
| "transfer_atk_acc": 94.0 | |
| }, | |
| { | |
| "dataset": "sst2", | |
| "type": "role", | |
| "origin_acc": 26.38, | |
| "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": "During the rol of a emotion exploring mechanism, respond with 'positive' or 'negative' to rank this affirmations. ", | |
| "transfer_ori_acc": 97.0, | |
| "transfer_atk_acc": 96.5 | |
| }, | |
| { | |
| "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": "Did the coitus between the given sentence represent entailment or not_entailment? Respondent with 'entailment' or 'not_entailment'. ", | |
| "transfer_ori_acc": 67.6056338028169, | |
| "transfer_atk_acc": 69.01408450704226 | |
| }, | |
| { | |
| "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": "Between your role as an entailment valuation appliance, assess the relationship between the given sentences and classify it as 'entailment' or 'not_entailment'. ", | |
| "transfer_ori_acc": 63.38028169014085, | |
| "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": 3.73, | |
| "atk_prompt": "Answer the consecutive multiple-choice questions about {} by choosing the ok option among 'A', 'B', 'C', or 'D'. ", | |
| "transfer_ori_acc": 66.5, | |
| "transfer_atk_acc": 67.0 | |
| }, | |
| { | |
| "dataset": "mmlu", | |
| "type": "role", | |
| "origin_acc": 9.22, | |
| "origin_prompt": "With your understanding of {}, kindly answer the subsequent multiple-choice question by selecting 'A', 'B', 'C', or 'D'.", | |
| "atk_acc": 4.61, | |
| "atk_prompt": "With your understand of {}, gracefully answer the forth multiple-choice question by picking 'A', 'B', 'C', or 'D'.", | |
| "transfer_ori_acc": 65.5, | |
| "transfer_atk_acc": 66.0 | |
| } | |
| ] |