Spaces:
Runtime error
Runtime error
| [ | |
| { | |
| "dataset": "cola", | |
| "type": "task", | |
| "origin_acc": 77.8, | |
| "origin_prompt": "Is the provided sentence grammatically correct? Respond with 'Acceptable' or 'Unacceptable'.", | |
| "atk_acc": 70.3, | |
| "atk_prompt": "Become the brought sentence grammatically correction? Reactions with 'Acceptable' or 'Unacceptable'. ", | |
| "transfer_ori_acc": 6.0, | |
| "transfer_atk_acc": 28.799999999999997 | |
| }, | |
| { | |
| "dataset": "cola", | |
| "type": "role", | |
| "origin_acc": 75.7, | |
| "origin_prompt": "While performing grammar analysis, classify the grammar of the following sentence as 'acceptable' for correct grammar or 'unacceptable' for incorrect grammar.", | |
| "atk_acc": 70.5, | |
| "atk_prompt": "If performing pronunciation analyzing, classify the grammar of the following condemnation as 'acceptable' for adequate jargon or 'unacceptable' for misspelled dictionary. ", | |
| "transfer_ori_acc": 49.9, | |
| "transfer_atk_acc": 26.900000000000002 | |
| }, | |
| { | |
| "dataset": "mrpc", | |
| "type": "task", | |
| "origin_acc": 83.09, | |
| "origin_prompt": "Evaluate whether the two provided sentences convey the same meaning by answering 'equivalent' or 'not_equivalent'.", | |
| "atk_acc": 78.92, | |
| "atk_prompt": "Estimation whether the two provided convictions despatch the same meaning by answers 'equivalent' or 'not_equivalent'. ", | |
| "transfer_ori_acc": 65.19607843137256, | |
| "transfer_atk_acc": 71.32352941176471 | |
| }, | |
| { | |
| "dataset": "mrpc", | |
| "type": "role", | |
| "origin_acc": 80.15, | |
| "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": 75.25, | |
| "atk_prompt": "In the role of a sentence likened psychoanalyst, assess the awarded sentences and indicate if they convey the same feeling by selecting 'equivalent' or 'not_equivalent'. ", | |
| "transfer_ori_acc": 68.87254901960785, | |
| "transfer_atk_acc": 60.049019607843135 | |
| }, | |
| { | |
| "dataset": "qnli", | |
| "type": "task", | |
| "origin_acc": 88.8, | |
| "origin_prompt": "Evaluate whether the given context supports the answer to the question by responding with 'entailment' or 'not_entailment'.", | |
| "atk_acc": 36.0, | |
| "atk_prompt": "Valuing whether the bestowed framework perpetuates the responded to the tura by retaliated with 'entailment' or 'not_entailment'. ", | |
| "transfer_ori_acc": 18.0, | |
| "transfer_atk_acc": 10.8 | |
| }, | |
| { | |
| "dataset": "qnli", | |
| "type": "role", | |
| "origin_acc": 88.8, | |
| "origin_prompt": "In the capacity of a language evaluator, examine if the given context justifies the answer to the question and indicate your assessment with 'entailment' or 'not_entailment'.", | |
| "atk_acc": 29.8, | |
| "atk_prompt": "Of the jurisdictional of a phraseology evaluator, exams if the handed regard vindicated the solution to the matter and clarified your examinations with 'entailment' or 'not_entailment'. ", | |
| "transfer_ori_acc": 34.4, | |
| "transfer_atk_acc": 8.0 | |
| }, | |
| { | |
| "dataset": "qqp", | |
| "type": "task", | |
| "origin_acc": 88.1, | |
| "origin_prompt": "textfooler", | |
| "atk_acc": 70.9, | |
| "atk_prompt": "Become the farther two subjects equivalent or not? Retaliated me with \"equivalent\" or \"not_equivalent\". ", | |
| "transfer_ori_acc": 48.3, | |
| "transfer_atk_acc": 35.0 | |
| }, | |
| { | |
| "dataset": "qqp", | |
| "type": "role", | |
| "origin_acc": 86.5, | |
| "origin_prompt": "As an instrument for question comparison evaluation, consider the questions and determine if their meaning is the same, responding with 'equivalent' for similar questions or 'not_equivalent' for different questions.", | |
| "atk_acc": 63.4, | |
| "atk_prompt": "As an tool for topic relation valuing, look the theme and identify if their connotation is the same, retaliated with 'equivalent' for similar question or 'not_equivalent' for other trouble. ", | |
| "transfer_ori_acc": 35.3, | |
| "transfer_atk_acc": 32.2 | |
| }, | |
| { | |
| "dataset": "rte", | |
| "type": "task", | |
| "origin_acc": 84.84, | |
| "origin_prompt": "Identify whether the given pair of sentences demonstrates entailment or not_entailment. Answer with 'entailment' or 'not_entailment'.", | |
| "atk_acc": 80.51, | |
| "atk_prompt": "Defined whether the made peers of sentences showings entailment or not_entailment. Reaction with 'entailment' or 'not_entailment'. ", | |
| "transfer_ori_acc": 7.2202166064981945, | |
| "transfer_atk_acc": 43.32129963898917 | |
| }, | |
| { | |
| "dataset": "rte", | |
| "type": "role", | |
| "origin_acc": 84.12, | |
| "origin_prompt": "Acting as an entailment detection instrument, determine if the given pair of sentences demonstrates entailment or not_entailment. Answer with 'entailment' or 'not_entailment'.", | |
| "atk_acc": 79.78, | |
| "atk_prompt": "Acting as an entailment detects instrument, defined if the given torque of sentences showcases entailment or not_entailment. Replies with 'entailment' or 'not_entailment'. ", | |
| "transfer_ori_acc": 4.332129963898916, | |
| "transfer_atk_acc": 45.48736462093863 | |
| }, | |
| { | |
| "dataset": "sst2", | |
| "type": "task", | |
| "origin_acc": 94.95, | |
| "origin_prompt": "Analyze the tone of this statement and respond with either 'positive' or 'negative'.", | |
| "atk_acc": 94.27, | |
| "atk_prompt": "Explore the tone of this affirmations and react with either 'positive' or 'negative'. ", | |
| "transfer_ori_acc": 12.5, | |
| "transfer_atk_acc": 1.0321100917431194 | |
| }, | |
| { | |
| "dataset": "sst2", | |
| "type": "role", | |
| "origin_acc": 95.53, | |
| "origin_prompt": "In the role of a sentiment analysis tool, respond with 'positive' or 'negative' to classify this statement.", | |
| "atk_acc": 94.04, | |
| "atk_prompt": "In the role of a emotions exploring toolbox, respond with 'positive' or 'negative' to sorted this affirmations. ", | |
| "transfer_ori_acc": 28.6697247706422, | |
| "transfer_atk_acc": 1.834862385321101 | |
| }, | |
| { | |
| "dataset": "wnli", | |
| "type": "task", | |
| "origin_acc": 64.79, | |
| "origin_prompt": "Assess the connection between the following sentences and classify it as 'entailment' or 'not_entailment'.", | |
| "atk_acc": 54.93, | |
| "atk_prompt": "Assess the connecting between the subsequent phrases and classify it as 'entailment' or 'not_entailment'. ", | |
| "transfer_ori_acc": 19.718309859154928, | |
| "transfer_atk_acc": 18.30985915492958 | |
| }, | |
| { | |
| "dataset": "wnli", | |
| "type": "role", | |
| "origin_acc": 66.2, | |
| "origin_prompt": "Functioning as an entailment evaluation tool, analyze the provided sentences and decide if their relationship is 'entailment' or 'not_entailment'.", | |
| "atk_acc": 56.34, | |
| "atk_prompt": "Functioning as an entailment evaluation tool, analyze the afforded sentences and chosen if their liaise is 'entailment' or 'not_entailment'. ", | |
| "transfer_ori_acc": 9.859154929577464, | |
| "transfer_atk_acc": 30.985915492957744 | |
| }, | |
| { | |
| "dataset": "mmlu", | |
| "type": "task", | |
| "origin_acc": 46.45, | |
| "origin_prompt": "For each multiple-choice question about {}, identify the correct answer by selecting 'A', 'B', 'C', or 'D'.", | |
| "atk_acc": 37.41, | |
| "atk_prompt": "About each multiple-choice question about {}, find the rectify rebuttal by choices 'A', 'B', 'C', or 'D'. ", | |
| "transfer_ori_acc": 6.560283687943262, | |
| "transfer_atk_acc": 7.446808510638298 | |
| }, | |
| { | |
| "dataset": "mmlu", | |
| "type": "role", | |
| "origin_acc": 46.99, | |
| "origin_prompt": "Considering your familiarity with {}, attend to the following multiple-choice question by picking 'A', 'B', 'C', or 'D'.", | |
| "atk_acc": 43.44, | |
| "atk_prompt": "Explored your familiarity with {}, participate to the next multiple-choice issues by pickup 'A', 'B', 'C', or 'D'.", | |
| "transfer_ori_acc": 8.156028368794328, | |
| "transfer_atk_acc": 6.382978723404255 | |
| } | |
| ] |