Spaces:
Runtime error
Runtime error
| [ | |
| { | |
| "dataset": "cola", | |
| "type": "task", | |
| "origin_acc": 80.5, | |
| "origin_prompt": "Examine the sentence and decide if its grammar is 'Acceptable' or 'Unacceptable'.", | |
| "atk_acc": 39.5, | |
| "atk_prompt": "Exams the sentence and defining if its jargon is 'Acceptable' or 'Unacceptable'. ", | |
| "transfer_ori_acc": 41.8, | |
| "transfer_atk_acc": 57.8 | |
| }, | |
| { | |
| "dataset": "cola", | |
| "type": "role", | |
| "origin_acc": 81.0, | |
| "origin_prompt": "In the role of a syntax analyzer, examine the grammar of the provided sentence and decide if it is correct, answering with 'acceptable' for grammatically correct sentences or 'unacceptable' for incorrect ones.", | |
| "atk_acc": 76.0, | |
| "atk_prompt": "Across the role of a syntax analyzer, examine the dictionary of the provided chastisement and decide if it is adequate, answered with 'acceptable' for grammatically correct sentences or 'unacceptable' for deceptive ones. ", | |
| "transfer_ori_acc": 3.4000000000000004, | |
| "transfer_atk_acc": 11.600000000000001 | |
| }, | |
| { | |
| "dataset": "mrpc", | |
| "type": "task", | |
| "origin_acc": 73.0, | |
| "origin_prompt": "Assess if the two given sentences have equivalent meanings by selecting 'equivalent' or 'not_equivalent'.", | |
| "atk_acc": 59.0, | |
| "atk_prompt": "Appraisal if the two accorded sentences enjoys equivalent connotation by choice 'equivalent' or 'not_equivalent'. ", | |
| "transfer_ori_acc": 69.36274509803921, | |
| "transfer_atk_acc": 69.36274509803921 | |
| }, | |
| { | |
| "dataset": "mrpc", | |
| "type": "role", | |
| "origin_acc": 71.5, | |
| "origin_prompt": "In the role of a textual comparison specialist, examine the given sentences and decide if they share the same meaning, responding with 'equivalent' or 'not_equivalent'.", | |
| "atk_acc": 57.0, | |
| "atk_prompt": "De the role of a textual comparisons scholar, revisited the given sentences and decide if they exchange the same feel, responding with 'equivalent' or 'not_equivalent'. ", | |
| "transfer_ori_acc": 69.36274509803921, | |
| "transfer_atk_acc": 55.14705882352941 | |
| }, | |
| { | |
| "dataset": "qnli", | |
| "type": "task", | |
| "origin_acc": 84.5, | |
| "origin_prompt": "Examine the context and question, and determine if the context logically implies the answer by selecting 'entailment' or 'not_entailment'.", | |
| "atk_acc": 63.5, | |
| "atk_prompt": "Discuss the background and question, and determine if the framework intuitively presupposes the answer by akhtar 'entailment' or 'not_entailment'. ", | |
| "transfer_ori_acc": 26.900000000000002, | |
| "transfer_atk_acc": 33.0 | |
| }, | |
| { | |
| "dataset": "qnli", | |
| "type": "role", | |
| "origin_acc": 85.5, | |
| "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": 68.5, | |
| "atk_prompt": "Iike a textual analyst, analyze if the submitted regard rationally implies the replies to the issuing and indicates your clout with 'entailment' or 'not_entailment'. ", | |
| "transfer_ori_acc": 31.4, | |
| "transfer_atk_acc": 12.4 | |
| }, | |
| { | |
| "dataset": "qqp", | |
| "type": "task", | |
| "origin_acc": 83.5, | |
| "origin_prompt": "Determine if the given pair of statements can be considered the same by responding with 'equivalent' or 'not_equivalent'.", | |
| "atk_acc": 80.0, | |
| "atk_prompt": "Determine if the given pair of representations can constitute felt the same by responding with 'equivalent' or 'not_equivalent'. ", | |
| "transfer_ori_acc": 29.9, | |
| "transfer_atk_acc": 32.9 | |
| }, | |
| { | |
| "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": 80.0, | |
| "atk_prompt": "Interim as a issues equivalence instrument, determine if the provided aspects are equivalent in meaning, answering with 'equivalent' for selfsame questions or 'not_equivalent' for dissimilar ones. ", | |
| "transfer_ori_acc": 34.599999999999994, | |
| "transfer_atk_acc": 32.5 | |
| }, | |
| { | |
| "dataset": "rte", | |
| "type": "task", | |
| "origin_acc": 84.5, | |
| "origin_prompt": "Does the relationship between the given sentences represent entailment or not_entailment? Respond with 'entailment' or 'not_entailment'.", | |
| "atk_acc": 79.5, | |
| "atk_prompt": "Do the coitus between the given sentences comprised entailment or not_entailment? Meet with 'entailment' or 'not_entailment'. ", | |
| "transfer_ori_acc": 46.20938628158845, | |
| "transfer_atk_acc": 44.4043321299639 | |
| }, | |
| { | |
| "dataset": "rte", | |
| "type": "role", | |
| "origin_acc": 83.0, | |
| "origin_prompt": "As an entailment identification system, examine the connection between the following sentences and respond with 'entailment' or 'not_entailment'.", | |
| "atk_acc": 79.5, | |
| "atk_prompt": "As an entailment identification system, revisited the connection between the following sentences and respondent with 'entailment' or 'not_entailment'. ", | |
| "transfer_ori_acc": 46.20938628158845, | |
| "transfer_atk_acc": 44.765342960288805 | |
| }, | |
| { | |
| "dataset": "sst2", | |
| "type": "task", | |
| "origin_acc": 96.0, | |
| "origin_prompt": "Read the provided excerpt and choose between 'positive' and 'negative' to describe its sentiment.", | |
| "atk_acc": 85.0, | |
| "atk_prompt": "Lu the rendered excerpt and withheld between 'positive' and 'negative' to describe its foreboding. ", | |
| "transfer_ori_acc": 1.261467889908257, | |
| "transfer_atk_acc": 3.4403669724770642 | |
| }, | |
| { | |
| "dataset": "sst2", | |
| "type": "role", | |
| "origin_acc": 97.5, | |
| "origin_prompt": "Emulating a sentiment classification system, indicate whether the provided text is 'positive' or 'negative'.", | |
| "atk_acc": 91.5, | |
| "atk_prompt": "Emulating a ambience classification mechanisms, describe whether the presented writings is 'positive' or 'negative'. ", | |
| "transfer_ori_acc": 22.93577981651376, | |
| "transfer_atk_acc": 3.211009174311927 | |
| }, | |
| { | |
| "dataset": "wnli", | |
| "type": "task", | |
| "origin_acc": 69.01, | |
| "origin_prompt": "Indicate if the connection between the following sentences is 'entailment' or 'not_entailment'.", | |
| "atk_acc": 59.15, | |
| "atk_prompt": "Indicate if the connection between the subsequently sentences is 'entailment' or 'not_entailment'. ", | |
| "transfer_ori_acc": 9.859154929577464, | |
| "transfer_atk_acc": 9.859154929577464 | |
| }, | |
| { | |
| "dataset": "wnli", | |
| "type": "role", | |
| "origin_acc": 66.2, | |
| "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": 57.75, | |
| "atk_prompt": "In the role of a semantic contacts analyzer, analysed the connecting between the given sentences and choose if they exhibit entailment or not_entailment. Answer with 'entailment' or 'not_entailment'. ", | |
| "transfer_ori_acc": 5.633802816901409, | |
| "transfer_atk_acc": 14.084507042253522 | |
| }, | |
| { | |
| "dataset": "mmlu", | |
| "type": "task", | |
| "origin_acc": 67.0, | |
| "origin_prompt": "Please respond to the multiple-choice question about {} by selecting the appropriate answer: 'A', 'B', 'C', or 'D'.", | |
| "atk_acc": 60.0, | |
| "atk_prompt": "Asking reactions to the multiple-choice question about {} by selecting the appropriate reacts: 'A', 'B', 'C', or 'D'. ", | |
| "transfer_ori_acc": 8.865248226950355, | |
| "transfer_atk_acc": 16.134751773049647 | |
| }, | |
| { | |
| "dataset": "mmlu", | |
| "type": "role", | |
| "origin_acc": 66.0, | |
| "origin_prompt": "With your knowledge of {}, tackle the following multiple-choice question by choosing 'A', 'B', 'C', or 'D'.", | |
| "atk_acc": 61.5, | |
| "atk_prompt": "From your acquaintances of {}, addressing the following multiple-choice question by choosing 'A', 'B', 'C', or 'D'.", | |
| "transfer_ori_acc": 8.865248226950355, | |
| "transfer_atk_acc": 10.28368794326241 | |
| } | |
| ] |