Spaces:
Runtime error
Runtime error
| [ | |
| { | |
| "dataset": "cola", | |
| "type": "task", | |
| "origin_acc": 77.5, | |
| "origin_prompt": "Determine if the grammar of the given sentence is 'Acceptable' or 'Unacceptable':", | |
| "atk_acc": 31.0, | |
| "atk_prompt": "Establishes if the jargon of the made punishments is 'Acceptable' or 'Unacceptable':", | |
| "transfer_ori_acc": 36.4, | |
| "transfer_atk_acc": 15.0 | |
| }, | |
| { | |
| "dataset": "cola", | |
| "type": "role", | |
| "origin_acc": 76.3, | |
| "origin_prompt": "As an instrument for grammar evaluation, consider the sentence and determine if its grammar is correct, responding with 'acceptable' for correct grammar or 'unacceptable' for incorrect grammar:", | |
| "atk_acc": 30.8, | |
| "atk_prompt": "Since an apparatus for language measured, envisage the convicts and identify if its language is correct, reaction with 'acceptable' for accurate jargon or 'unacceptable' for unsound pronunciation:", | |
| "transfer_ori_acc": 36.199999999999996, | |
| "transfer_atk_acc": 19.8 | |
| }, | |
| { | |
| "dataset": "mrpc", | |
| "type": "task", | |
| "origin_acc": 82.11, | |
| "origin_prompt": "Do these two sentences have the same underlying meaning? Respond with 'equivalent' or 'not_equivalent'.", | |
| "atk_acc": 53.68, | |
| "atk_prompt": "Ca these two condemning ont the same main meaning? Reactions with 'equivalent' or 'not_equivalent'. ", | |
| "transfer_ori_acc": 54.90196078431373, | |
| "transfer_atk_acc": 32.59803921568628 | |
| }, | |
| { | |
| "dataset": "mrpc", | |
| "type": "role", | |
| "origin_acc": 81.62, | |
| "origin_prompt": "As a language comparison expert, examine the given pair of sentences and decide if their meanings align, answering with 'equivalent' or 'not_equivalent'.", | |
| "atk_acc": 12.01, | |
| "atk_prompt": "As a language compared professional, reviews the given torque of sentences and picked if their sens unify, address with 'equivalent' or 'not_equivalent'. ", | |
| "transfer_ori_acc": 63.23529411764706, | |
| "transfer_atk_acc": 6.61764705882353 | |
| }, | |
| { | |
| "dataset": "qnli", | |
| "type": "task", | |
| "origin_acc": 89.8, | |
| "origin_prompt": "Evaluate whether the given context supports the answer to the question by responding with 'entailment' or 'not_entailment'.", | |
| "atk_acc": 41.4, | |
| "atk_prompt": "Estimation whether the gave backgrounds perpetuates the answered to the trouble by responses with 'entailment' or 'not_entailment'. ", | |
| "transfer_ori_acc": 26.5, | |
| "transfer_atk_acc": 4.3999999999999995 | |
| }, | |
| { | |
| "dataset": "qnli", | |
| "type": "role", | |
| "origin_acc": 89.4, | |
| "origin_prompt": "As a semantic interpreter, assess whether the provided context supports the answer to the given question and answer with 'entailment' or 'not_entailment'.", | |
| "atk_acc": 3.3, | |
| "atk_prompt": "Iike a semantic performers, valuing whether the afforded ambient perpetuates the answer to the rendered item and cope with 'entailment' or 'not_entailment'. ", | |
| "transfer_ori_acc": 8.7, | |
| "transfer_atk_acc": 4.1000000000000005 | |
| }, | |
| { | |
| "dataset": "qqp", | |
| "type": "task", | |
| "origin_acc": 87.7, | |
| "origin_prompt": "Assess whether the following statements are identical in meaning by answering 'equivalent' or 'not_equivalent'.", | |
| "atk_acc": 18.9, | |
| "atk_prompt": "Valuing whether the later languages are comparable in sinn by cope 'equivalent' or 'not_equivalent'. ", | |
| "transfer_ori_acc": 30.2, | |
| "transfer_atk_acc": 0.8 | |
| }, | |
| { | |
| "dataset": "qqp", | |
| "type": "role", | |
| "origin_acc": 86.9, | |
| "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": 73.8, | |
| "atk_prompt": "About the rol of a question likeness analyzer, examine the mean of the conferred topic and identifying if they are equivalent, retaliated with 'equivalent' for equivalent trouble or 'not_equivalent' for other topics. ", | |
| "transfer_ori_acc": 23.3, | |
| "transfer_atk_acc": 14.000000000000002 | |
| }, | |
| { | |
| "dataset": "rte", | |
| "type": "task", | |
| "origin_acc": 86.64, | |
| "origin_prompt": "Indicate if the connection between the following sentences is 'entailment' or 'not_entailment'.", | |
| "atk_acc": 80.87, | |
| "atk_prompt": "Portrays if the login between the following punishments is 'entailment' or 'not_entailment'.", | |
| "transfer_ori_acc": 38.26714801444043, | |
| "transfer_atk_acc": 3.6101083032490973 | |
| }, | |
| { | |
| "dataset": "rte", | |
| "type": "role", | |
| "origin_acc": 84.84, | |
| "origin_prompt": "In the capacity of an entailment assessment system, indicate if the link between the following sentences is 'entailment' or 'not_entailment':", | |
| "atk_acc": 79.06, | |
| "atk_prompt": "About the capacity of an entailment weighed system, specified if the link between the following phrases is 'entailment' or 'not_entailment':", | |
| "transfer_ori_acc": 43.682310469314075, | |
| "transfer_atk_acc": 25.992779783393498 | |
| }, | |
| { | |
| "dataset": "sst2", | |
| "type": "task", | |
| "origin_acc": 94.95, | |
| "origin_prompt": "Given the context of this text, indicate if the emotion conveyed is 'positive' or 'negative':", | |
| "atk_acc": 84.29, | |
| "atk_prompt": "Made the background of this version, depicts if the passion recharged is 'positive' or 'negative': ", | |
| "transfer_ori_acc": 29.472477064220183, | |
| "transfer_atk_acc": 11.353211009174311 | |
| }, | |
| { | |
| "dataset": "sst2", | |
| "type": "role", | |
| "origin_acc": 95.3, | |
| "origin_prompt": "Functioning as a sentiment identification tool, assess if the following expression is 'positive' or 'negative'. Classify:", | |
| "atk_acc": 25.46, | |
| "atk_prompt": "Functions as a emotion defining instrumentation, valuing if the next voicing is 'positive' or 'negative'. Classification: ", | |
| "transfer_ori_acc": 38.646788990825684, | |
| "transfer_atk_acc": 24.541284403669724 | |
| }, | |
| { | |
| "dataset": "wnli", | |
| "type": "task", | |
| "origin_acc": 66.2, | |
| "origin_prompt": "Are the following two sentences entailment or not_entailment? Answer me with \"entailment\" or \"not_entailment\", just one word.", | |
| "atk_acc": 56.34, | |
| "atk_prompt": "Be the following two phrases entailment or not_entailment? Responded me with \"entailment\" or \"not_entailment\", just one verb. ", | |
| "transfer_ori_acc": 25.352112676056336, | |
| "transfer_atk_acc": 32.3943661971831 | |
| }, | |
| { | |
| "dataset": "wnli", | |
| "type": "role", | |
| "origin_acc": 64.79, | |
| "origin_prompt": "In the capacity of an entailment assessment system, indicate if the link between the following sentences is 'entailment' or 'not_entailment':", | |
| "atk_acc": 56.34, | |
| "atk_prompt": "Among the capacity of an entailment analysis system, indicate if the attach between the subsequently sentences is 'entailment' or 'not_entailment':", | |
| "transfer_ori_acc": 43.66197183098591, | |
| "transfer_atk_acc": 42.25352112676056 | |
| }, | |
| { | |
| "dataset": "mmlu", | |
| "type": "task", | |
| "origin_acc": 45.74, | |
| "origin_prompt": "For each multiple-choice question about {}, identify the correct answer by selecting 'A', 'B', 'C', or 'D'.", | |
| "atk_acc": 37.06, | |
| "atk_prompt": "By any multiple-choice question about {}, locate the corrected riposte by akhtar 'A', 'B', 'C', or 'D'. ", | |
| "transfer_ori_acc": 22.69503546099291, | |
| "transfer_atk_acc": 22.872340425531913 | |
| }, | |
| { | |
| "dataset": "mmlu", | |
| "type": "role", | |
| "origin_acc": 44.86, | |
| "origin_prompt": "Utilizing your expertise in {}, answer the following multiple-choice question by picking 'A', 'B', 'C', or 'D'.", | |
| "atk_acc": 40.96, | |
| "atk_prompt": "Utilise your expertise in {}, meet the next multiple-choice question by collection 'A', 'B', 'C', or 'D'.", | |
| "transfer_ori_acc": 20.74468085106383, | |
| "transfer_atk_acc": 25.177304964539005 | |
| } | |
| ] |