Spaces:
Runtime error
Runtime error
| [ | |
| { | |
| "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": 77.0, | |
| "transfer_atk_acc": 36.0 | |
| }, | |
| { | |
| "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": 30.9, | |
| "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": 79.0, | |
| "transfer_atk_acc": 0.0 | |
| }, | |
| { | |
| "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": 73.5, | |
| "transfer_atk_acc": 69.5 | |
| }, | |
| { | |
| "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": 75.0, | |
| "transfer_atk_acc": 4.5 | |
| }, | |
| { | |
| "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": 78.0, | |
| "transfer_atk_acc": 36.0 | |
| }, | |
| { | |
| "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": 65.5, | |
| "transfer_atk_acc": 9.0 | |
| }, | |
| { | |
| "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": 81.0, | |
| "transfer_atk_acc": 74.5 | |
| }, | |
| { | |
| "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": 80.5, | |
| "transfer_atk_acc": 81.5 | |
| }, | |
| { | |
| "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": 81.0, | |
| "transfer_atk_acc": 76.5 | |
| }, | |
| { | |
| "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": 78.0, | |
| "transfer_atk_acc": 75.5 | |
| }, | |
| { | |
| "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": 86.5, | |
| "transfer_atk_acc": 0.0 | |
| }, | |
| { | |
| "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": 92.5, | |
| "transfer_atk_acc": 90.0 | |
| }, | |
| { | |
| "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": 64.7887323943662, | |
| "transfer_atk_acc": 63.38028169014085 | |
| }, | |
| { | |
| "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": 57.74647887323944, | |
| "transfer_atk_acc": 49.29577464788733 | |
| }, | |
| { | |
| "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": 63.0, | |
| "transfer_atk_acc": 10.0 | |
| }, | |
| { | |
| "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": 60.0, | |
| "transfer_atk_acc": 59.5 | |
| }, | |
| { | |
| "dataset": "squad_v2", | |
| "type": "task", | |
| "origin_acc": 87.82, | |
| "origin_prompt": "Search the context for the most relevant answer. If the answer cannot be found, respond with 'unanswerable'.", | |
| "atk_acc": 36.51, | |
| "atk_prompt": "return the topic for the most mentioned question. then the answer cannot be found, respond with 'unanswerable'.", | |
| "transfer_ori_acc": 61.62386143989461, | |
| "transfer_atk_acc": 63.478546402546655 | |
| }, | |
| { | |
| "dataset": "squad_v2", | |
| "type": "role", | |
| "origin_acc": 88.05, | |
| "origin_prompt": "As an authority on the context, locate the most accurate answer. If the context doesn't contain the answer, mention 'unanswerable'.", | |
| "atk_acc": 42.92, | |
| "atk_prompt": "in an authority on the context, discover the most incorrect explanation. ensure the person doesn't contains the answer, mention 'unanswerable'.", | |
| "transfer_ori_acc": 57.818138335095256, | |
| "transfer_atk_acc": 35.36431912991652 | |
| }, | |
| { | |
| "dataset": "iwslt", | |
| "type": "task", | |
| "origin_acc": 0.14, | |
| "origin_prompt": "Please perform a translation of the given sentence, converting it from {} to {}:", | |
| "atk_acc": 0.13, | |
| "atk_prompt": "Please perform a translation of the given citation, converting it from {} to {}:", | |
| "transfer_ori_acc": 0.21840008360286153, | |
| "transfer_atk_acc": 0.2179261989361023 | |
| }, | |
| { | |
| "dataset": "iwslt", | |
| "type": "role", | |
| "origin_acc": 0.14, | |
| "origin_prompt": "In the capacity of a proficient translator, please change the following sentence from {} to {}:", | |
| "atk_acc": 0.11, | |
| "atk_prompt": "i the capacity of a possessed translator, may modification the following sentence from {} to {}: ", | |
| "transfer_ori_acc": 0.22335240384171567, | |
| "transfer_atk_acc": 0.21951448904038018 | |
| }, | |
| { | |
| "dataset": "un_multi", | |
| "type": "task", | |
| "origin_acc": 0.27, | |
| "origin_prompt": "Convert the following sentence from its original {} language to the target language {}:", | |
| "atk_acc": 0.21, | |
| "atk_prompt": "refer the following sentence from its original {} language to the targets i {}:", | |
| "transfer_ori_acc": 0.32648562280284094, | |
| "transfer_atk_acc": 0.32318435707787674 | |
| }, | |
| { | |
| "dataset": "un_multi", | |
| "type": "role", | |
| "origin_acc": 0.27, | |
| "origin_prompt": "As a qualified translator, convert the given sentence from its original {} language to the target language {}:", | |
| "atk_acc": 0.17, | |
| "atk_prompt": "while a reflex translator, reverse the given sentence from its original {} language to the target languages {}: ", | |
| "transfer_ori_acc": 0.3295374598940522, | |
| "transfer_atk_acc": 0.3374240386421357 | |
| }, | |
| { | |
| "dataset": "math", | |
| "type": "task", | |
| "origin_acc": 14.37, | |
| "origin_prompt": "Obtain the result for this math question regarding {}:", | |
| "atk_acc": 2.5, | |
| "atk_prompt": "Obtain the procedure for this math question regarding {}:", | |
| "transfer_ori_acc": 6.875000000000001, | |
| "transfer_atk_acc": 0.625 | |
| }, | |
| { | |
| "dataset": "math", | |
| "type": "role", | |
| "origin_acc": 13.12, | |
| "origin_prompt": "As a mathematics instructor, calculate the answer to the following problem related to {}:", | |
| "atk_acc": 1.88, | |
| "atk_prompt": "As a mathematics instructor, calculate the sum to the following problem related to {}: ", | |
| "transfer_ori_acc": 5.0, | |
| "transfer_atk_acc": 2.5 | |
| } | |
| ] |