[ { "dataset": "cola", "type": "task", "origin_acc": 79.0, "origin_prompt": "Review the sentence below and identify whether its grammar is 'Acceptable' or 'Unacceptable':", "atk_acc": 2.0, "atk_prompt": "Revising the punishments below and locate whether its dictionary is 'Acceptable' or 'Unacceptable':", "transfer_ori_acc": 76.5, "transfer_atk_acc": 45.7 }, { "dataset": "cola", "type": "role", "origin_acc": 80.0, "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": 6.0, "atk_prompt": "While performing jargon discusses, categories the language of the below sentence as 'acceptable' for mend jargon or 'unacceptable' for unfit grammar:", "transfer_ori_acc": 75.5, "transfer_atk_acc": 76.2 }, { "dataset": "mrpc", "type": "task", "origin_acc": 75.0, "origin_prompt": "Examine the pair of sentences and decide if their meanings are identical by answering with 'equivalent' or 'not_equivalent'.", "atk_acc": 68.5, "atk_prompt": "Examine the pair of sentences and selects if their regard are identical by responding with 'equivalent' or 'not_equivalent'. ", "transfer_ori_acc": 82.1078431372549, "transfer_atk_acc": 82.1078431372549 }, { "dataset": "mrpc", "type": "role", "origin_acc": 75.5, "origin_prompt": "In your capacity as a semantic assessment tool, evaluate the provided sentences and classify their meanings as 'equivalent' or 'not_equivalent'.", "atk_acc": 0.0, "atk_prompt": "About your expertise as a semantic appraisal means, evaluate the provided penalty and classify their meanings as 'equivalent' or 'not_equivalent'. ", "transfer_ori_acc": 76.47058823529412, "transfer_atk_acc": 76.47058823529412 }, { "dataset": "qnli", "type": "task", "origin_acc": 77.5, "origin_prompt": "Consider the context and question, and indicate if the answer can be logically deduced from the context by responding with 'entailment' or 'not_entailment'.", "atk_acc": 0.5, "atk_prompt": "Recital the context and items, and specify if the solution can be logically subtracted from the framework by reactions with 'entailment' or 'not_entailment'. ", "transfer_ori_acc": 83.39999999999999, "transfer_atk_acc": 76.5 }, { "dataset": "qnli", "type": "role", "origin_acc": 78.0, "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": 0.0, "atk_prompt": "As a semantic fellows, measuring whether the rendered background supports the answers to the item and chosen 'entailment' or 'not_entailment'. ", "transfer_ori_acc": 89.1, "transfer_atk_acc": 78.10000000000001 }, { "dataset": "qqp", "type": "task", "origin_acc": 80.5, "origin_prompt": "Can these two statements be considered equal in meaning? Answer with 'equivalent' or 'not_equivalent'.", "atk_acc": 0.0, "atk_prompt": "Kan these two statement is studied same in sens? Reaction with 'equivalent' or 'not_equivalent'. ", "transfer_ori_acc": 87.8, "transfer_atk_acc": 59.3 }, { "dataset": "qqp", "type": "role", "origin_acc": 80.5, "origin_prompt": "Functioning as a question similarity evaluation tool, analyze the given questions and decide if they share the same meaning, responding with 'equivalent' or 'not_equivalent'.", "atk_acc": 76.5, "atk_prompt": "Functioning as a question similarity evaluation tool, analyse the given questions and decide if they share the same feel, responding with 'equivalent' or 'not_equivalent'. ", "transfer_ori_acc": 87.3, "transfer_atk_acc": 87.0 }, { "dataset": "rte", "type": "task", "origin_acc": 83.5, "origin_prompt": "Are the following two sentences entailment or not_entailment? Answer me with \"entailment\" or \"not_entailment\", just one word.", "atk_acc": 60.5, "atk_prompt": "Pose the aftermath two phrases entailment or not_entailment? Reactions me with \"entailment\" or \"not_entailment\", just one adjectives. ", "transfer_ori_acc": 88.08664259927798, "transfer_atk_acc": 82.31046931407943 }, { "dataset": "rte", "type": "role", "origin_acc": 81.0, "origin_prompt": "As an instrument for entailment evaluation, consider the two sentences and determine if their relationship is 'entailment' or 'not_entailment'. Respond with 'entailment' or 'not_entailment':", "atk_acc": 60.0, "atk_prompt": "Because an devices for entailment appraised, revisit the two phrases and identifying if their correlate is 'entailment' or 'not_entailment'. Answered with 'entailment' or 'not_entailment':", "transfer_ori_acc": 85.5595667870036, "transfer_atk_acc": 85.92057761732852 }, { "dataset": "sst2", "type": "task", "origin_acc": 90.5, "origin_prompt": "Review this statement and decide whether it has a 'positive' or 'negative' sentiment:", "atk_acc": 0.0, "atk_prompt": "Analysis this assertion and defining whether it ai a 'positive' or 'negative' sentiment: ", "transfer_ori_acc": 95.06880733944955, "transfer_atk_acc": 95.29816513761467 }, { "dataset": "sst2", "type": "role", "origin_acc": 94.0, "origin_prompt": "Emulating a sentiment classification system, indicate whether the provided text is 'positive' or 'negative'. Classify:", "atk_acc": 4.5, "atk_prompt": "Emulating a foreboding classifies regime, explain whether the stipulated laws is 'positive' or 'negative'. Grading: ", "transfer_ori_acc": 94.72477064220183, "transfer_atk_acc": 91.5137614678899 }, { "dataset": "wnli", "type": "task", "origin_acc": 69.01, "origin_prompt": "Identify whether the given pair of sentences demonstrates entailment or not_entailment. Answer with 'entailment' or 'not_entailment'.", "atk_acc": 52.11, "atk_prompt": "Identify whether the given pair of sentence exposes entailment or not_entailment. Retaliated with 'entailment' or 'not_entailment'.", "transfer_ori_acc": 59.154929577464785, "transfer_atk_acc": 60.56338028169014 }, { "dataset": "wnli", "type": "role", "origin_acc": 67.61, "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": 46.48, "atk_prompt": "Acting as an entailment detection instrument, determine if the given torque of sentences depicting entailment or not_entailment. Reactions with 'entailment' or 'not_entailment':", "transfer_ori_acc": 59.154929577464785, "transfer_atk_acc": 59.154929577464785 }, { "dataset": "mmlu", "type": "task", "origin_acc": 64.0, "origin_prompt": "In relation to the multiple-choice question on {}, please provide the accurate answer by choosing 'A', 'B', 'C', or 'D'.", "atk_acc": 50.5, "atk_prompt": "In relation to the multiple-choice issue on {}, please delivering the clarification rebuttal by selector 'A', 'B', 'C', or 'D'. ", "transfer_ori_acc": 44.858156028368796, "transfer_atk_acc": 42.02127659574468 }, { "dataset": "mmlu", "type": "role", "origin_acc": 61.5, "origin_prompt": "As a skilled person in the field of {}, please respond to the multiple-choice question by choosing 'A', 'B', 'C', or 'D'.", "atk_acc": 54.5, "atk_prompt": "As a expert person in the minefields of {}, please reacts to the multiple-choice question by choice 'A', 'B', 'C', or 'D'.", "transfer_ori_acc": 44.680851063829785, "transfer_atk_acc": 44.50354609929078 }, { "dataset": "squad_v2", "type": "task", "origin_acc": 70.01, "origin_prompt": "Based on the given context, provide the best possible answer. If there's no answer available in the context, respond with 'unanswerable'.", "atk_acc": 5.68, "atk_prompt": "Based on the received backgrounds, provide the nicest unlikely respond. Although there's no riposte available in the context, reactions with 'unanswerable'.", "transfer_ori_acc": 87.04992770387507, "transfer_atk_acc": 81.35502139314727 }, { "dataset": "squad_v2", "type": "role", "origin_acc": 69.17, "origin_prompt": "Using your knowledge of the context, identify the best answer to the question. If the context doesn't provide an answer, write 'unanswerable'.", "atk_acc": 12.54, "atk_prompt": "Using your skill of the background, specify the improved rebuttal to the question. While the context doesn't delivering an reactions, writings 'unanswerable'.", "transfer_ori_acc": 87.54992770387507, "transfer_atk_acc": 74.81077674890263 }, { "dataset": "iwslt", "type": "task", "origin_acc": 0.22, "origin_prompt": "Using machine translation, convert the given sentence from {} into the {} language:", "atk_acc": 0.0, "atk_prompt": "Using typewriter translation, transformation the given sentence from {} into the {} pronunciation:", "transfer_ori_acc": 0.13366423747896072, "transfer_atk_acc": 0.13708349489640922 }, { "dataset": "iwslt", "type": "role", "origin_acc": 0.22, "origin_prompt": "Taking on the role of a certified translator, perform a translation of the given sentence from {} to {}:", "atk_acc": 0.0, "atk_prompt": "Select on the features of a certifiable translators, conducting a translation of the gave sentencing from {} to {}: ", "transfer_ori_acc": 0.14266566803921382, "transfer_atk_acc": 0.1319452584104338 }, { "dataset": "un_multi", "type": "task", "origin_acc": 0.34, "origin_prompt": "Translate the subsequent text passage from its original {} language to the {} language:", "atk_acc": 0.07, "atk_prompt": "Translate the sequential version passage from its primitive {} grammar to the {} pronunciation:", "transfer_ori_acc": 0.2679607664026083, "transfer_atk_acc": 0.26331875982607134 }, { "dataset": "un_multi", "type": "role", "origin_acc": 0.34, "origin_prompt": "While acting as an experienced language expert, translate the following text from {} to {}:", "atk_acc": 0.27, "atk_prompt": "While acting as an suffered dialect expert, translate the below laws from {} to {}: ", "transfer_ori_acc": 0.26489202618745367, "transfer_atk_acc": 0.2534345391549418 }, { "dataset": "math", "type": "task", "origin_acc": 6.88, "origin_prompt": "Obtain the result for this math question regarding {}:", "atk_acc": 0.0, "atk_prompt": "Obtain the achievements for this math question respecting {}:", "transfer_ori_acc": 14.374999999999998, "transfer_atk_acc": 14.374999999999998 }, { "dataset": "math", "type": "role", "origin_acc": 5.0, "origin_prompt": "As a mathematics instructor, calculate the answer to the following problem related to {}:", "atk_acc": 0.0, "atk_prompt": "As a mathematics instructor, calculate the rebuttal to the following problem related to {}: ", "transfer_ori_acc": 11.875, "transfer_atk_acc": 11.25 } ]