[ { "dataset": "cola", "type": "task", "origin_acc": 77.9, "origin_prompt": "Examine the given sentence and decide if it is grammatically sound. Answer with either 'Acceptable' or 'Unacceptable':", "atk_acc": 30.9, "atk_prompt": "examine the english plural and say if it is grammaticalmost sound. Answer with neither 'Acceptable' or 'Unacceptable':", "transfer_ori_acc": 50.0, "transfer_atk_acc": 41.099999999999994 }, { "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": 30.9, "atk_prompt": "for an organ for linguistic evaluation, write the movie and question if its grammar is incorrect, and with 'acceptable' for new grammar or 'unacceptable' for unstable grammar:", "transfer_ori_acc": 36.199999999999996, "transfer_atk_acc": 44.4 }, { "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": 16.67, "atk_prompt": "do these two clauses have the same underlying meanings? deal with 'equivalent' or 'not_equivalent'. ", "transfer_ori_acc": 54.90196078431373, "transfer_atk_acc": 18.38235294117647 }, { "dataset": "mrpc", "type": "role", "origin_acc": 82.6, "origin_prompt": "In your capacity as a semantic comparison tool, examine the given sentences and decide if their meanings are identical, responding with 'equivalent' or 'not_equivalent'.", "atk_acc": 9.07, "atk_prompt": "using your capacity as a semantic relations member, determine the given words and decide if their meanings are consecutive, comparison with 'equivalent' or 'not_equivalent'. ", "transfer_ori_acc": 64.2156862745098, "transfer_atk_acc": 51.71568627450981 }, { "dataset": "qnli", "type": "task", "origin_acc": 88.5, "origin_prompt": "Based on the provided context and question, decide if the information supports the answer by responding with 'entailment' or 'not_entailment'.", "atk_acc": 27.6, "atk_prompt": "following on the supplied context and questioning, save if the information states the response by simply with 'entailment' or 'not_entailment'. ", "transfer_ori_acc": 38.4, "transfer_atk_acc": 9.6 }, { "dataset": "qnli", "type": "role", "origin_acc": 89.2, "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": 11.8, "atk_prompt": "as a textual analyst, scrutiny if the following means logical) implies the reply to the answer and cross your r with 'entailment' or 'not_entailment'. ", "transfer_ori_acc": 13.8, "transfer_atk_acc": 6.9 }, { "dataset": "qqp", "type": "task", "origin_acc": 88.1, "origin_prompt": "Are the following two questions equivalent or not? Answer me with \"equivalent\" or \"not_equivalent\".", "atk_acc": 80.2, "atk_prompt": "to the next enough being equivalent or not? Answer me with \"equivalent\" or \"not_equivalent\". ", "transfer_ori_acc": 23.9, "transfer_atk_acc": 19.3 }, { "dataset": "qqp", "type": "role", "origin_acc": 87.7, "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": 72.2, "atk_prompt": "t as a question equal instrument, determine if the program questions are equivalent in semantic, asking with 'equivalent' for analogous question or 'not_equivalent' for nonssimicomplex times. ", "transfer_ori_acc": 25.0, "transfer_atk_acc": 17.9 }, { "dataset": "rte", "type": "task", "origin_acc": 86.64, "origin_prompt": "Are the following two sentences entailment or not_entailment? Answer me with \"entailment\" or \"not_entailment\", just one word.", "atk_acc": 81.59, "atk_prompt": "be the following deux verbs entailment or not_entailment? asking me with \"entailment\" or \"not_entailment\", just one word. ", "transfer_ori_acc": 27.075812274368232, "transfer_atk_acc": 34.29602888086642 }, { "dataset": "rte", "type": "role", "origin_acc": 84.84, "origin_prompt": "While performing entailment analysis, classify the relationship between the provided sentences as 'entailment' or 'not_entailment':", "atk_acc": 78.7, "atk_prompt": "While performing entailment analysis, construct the relationship between the and sentence as 'entailment' or 'not_entailment':", "transfer_ori_acc": 23.104693140794225, "transfer_atk_acc": 15.162454873646208 }, { "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": 92.89, "atk_prompt": "give the context of this context, and if the emotion recorded is 'positive' or 'negative': ", "transfer_ori_acc": 29.472477064220183, "transfer_atk_acc": 22.24770642201835 }, { "dataset": "sst2", "type": "role", "origin_acc": 95.41, "origin_prompt": "In the role of a sentiment analysis tool, respond with 'positive' or 'negative' to classify this statement:", "atk_acc": 89.79, "atk_prompt": "how the role of a compliment analysis tool, responses with 'positive' or 'negative' to mood this statement: ", "transfer_ori_acc": 32.798165137614674, "transfer_atk_acc": 39.10550458715596 }, { "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": 54.93, "atk_prompt": "are the following analogous sentence entailment or not_entailment? Answer me with \"entailment\" or \"not_entailment\", just one verb. ", "transfer_ori_acc": 25.352112676056336, "transfer_atk_acc": 35.2112676056338 }, { "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": "h the capacity of an entailment assessment system, indicate if the link between the following verb is 'entailment' or 'not_entailment':", "transfer_ori_acc": 43.66197183098591, "transfer_atk_acc": 12.676056338028168 }, { "dataset": "mmlu", "type": "task", "origin_acc": 45.57, "origin_prompt": "For the multiple-choice question related to {}, please choose the most accurate answer from 'A', 'B', 'C', or 'D'.", "atk_acc": 16.84, "atk_prompt": "For the multiple-choice choice similar to {}, please find the most inaccurate questions from 'A', 'B', 'C', or 'D'. ", "transfer_ori_acc": 18.79432624113475, "transfer_atk_acc": 22.5177304964539 }, { "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": 3.19, "atk_prompt": "Utilizing your expertise in {}, write the following multiple-choices question by each 'A', 'B', 'C', or 'D'.", "transfer_ori_acc": 20.74468085106383, "transfer_atk_acc": 30.141843971631204 } ]