[ { "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": 86.6, "transfer_atk_acc": 85.8 }, { "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": 86.4, "transfer_atk_acc": 86.6 }, { "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": 85.7843137254902, "transfer_atk_acc": 85.04901960784314 }, { "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": 86.27450980392157, "transfer_atk_acc": 86.51960784313727 }, { "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": 94.0, "transfer_atk_acc": 82.3 }, { "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": 93.60000000000001, "transfer_atk_acc": 81.39999999999999 }, { "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": 84.6, "transfer_atk_acc": 88.7 }, { "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": 89.0, "transfer_atk_acc": 88.9 }, { "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": 93.14079422382672, "transfer_atk_acc": 92.7797833935018 }, { "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": 93.50180505415162, "transfer_atk_acc": 92.4187725631769 }, { "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": 96.78899082568807, "transfer_atk_acc": 96.78899082568807 }, { "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": 96.67431192660551, "transfer_atk_acc": 96.55963302752293 }, { "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": 76.05633802816901, "transfer_atk_acc": 76.05633802816901 }, { "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": 76.05633802816901, "transfer_atk_acc": 76.05633802816901 }, { "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": 53.191489361702125, "transfer_atk_acc": 49.46808510638298 }, { "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": 54.43262411347518, "transfer_atk_acc": 53.54609929078015 }, { "dataset": "squad_v2", "type": "task", "origin_acc": 87.91, "origin_prompt": "From the context, provide the most precise answer. If the answer is not in the context, respond with 'unanswerable'.", "atk_acc": 86.05, "atk_prompt": "Against the context, give the most correct answer. If the solution is not in the context, respond with 'unanswerable'.", "transfer_ori_acc": 89.38229949874687, "transfer_atk_acc": 89.88229949874687 }, { "dataset": "squad_v2", "type": "role", "origin_acc": 87.05, "origin_prompt": "As a subject matter expert, extract the correct answer from the context. If an answer is not present, indicate 'unanswerable'.", "atk_acc": 85.45, "atk_prompt": "As a subject matter expert, extract the correct reacts from the context. If an answer is not present, indicate 'unanswerable'.", "transfer_ori_acc": 89.54896616541353, "transfer_atk_acc": 90.54896616541353 }, { "dataset": "iwslt", "type": "task", "origin_acc": 0.22, "origin_prompt": "Convert the following sentence from its original {} language to the target language {}.", "atk_acc": 0.13, "atk_prompt": "Conversion the later conviction from its indigenous {} vocabulary to the blanco tongues {}. ", "transfer_ori_acc": 0.23981220411098694, "transfer_atk_acc": 0.19057711840277197 }, { "dataset": "iwslt", "type": "role", "origin_acc": 0.22, "origin_prompt": "In the role of a language expert, perform a machine translation for the provided sentence, changing it from {} to {}.", "atk_acc": 0.16, "atk_prompt": "In the role of a languages specializing, exerting a machine converting for the handed pity, metamorphosis it from {} to {}. ", "transfer_ori_acc": 0.236844571841243, "transfer_atk_acc": 0.19421293922384184 }, { "dataset": "un_multi", "type": "task", "origin_acc": 0.31, "origin_prompt": "Convert the following sentence from its original {} language to the target language {}.", "atk_acc": 0.22, "atk_prompt": "Convert the below sentence from its indigenous {} language to the blanco language {}. ", "transfer_ori_acc": 0.3527971649826467, "transfer_atk_acc": 0.3519334378680938 }, { "dataset": "un_multi", "type": "role", "origin_acc": 0.31, "origin_prompt": "Taking on the role of a certified translator, perform a translation of the given sentence from {} to {}.", "atk_acc": 0.26, "atk_prompt": "Taking on the role of a attest translator, implement a interpreters of the gave sanction from {} to {}. ", "transfer_ori_acc": 0.35510202593913104, "transfer_atk_acc": 0.3537216698989885 }, { "dataset": "math", "type": "task", "origin_acc": 17.5, "origin_prompt": "Find the solution for this mathematical challenge with {}.", "atk_acc": 15.0, "atk_prompt": "Find the resolutions for this mathematical challenge with {}. ", "transfer_ori_acc": 15.625, "transfer_atk_acc": 15.0 }, { "dataset": "math", "type": "role", "origin_acc": 18.12, "origin_prompt": "Embodying a mathematics advisor, find the answer to the following math problem with {}.", "atk_acc": 13.75, "atk_prompt": "Embodying a mathematics advice, find the rebuttal to the following math problem with {}. ", "transfer_ori_acc": 15.0, "transfer_atk_acc": 11.25 } ]