Spaces:
Runtime error
Runtime error
| [ | |
| { | |
| "dataset": "cola", | |
| "type": "task", | |
| "origin_acc": 81.0, | |
| "origin_prompt": "Analyze the provided sentence and classify its grammatical correctness as 'Acceptable' or 'Unacceptable'.", | |
| "atk_acc": 59.0, | |
| "atk_prompt": "Analyze the reported speech and classify its inclusive correcting as 'Acceptable' or 'Unacceptable'. ", | |
| "transfer_ori_acc": 86.0, | |
| "transfer_atk_acc": 78.0 | |
| }, | |
| { | |
| "dataset": "cola", | |
| "type": "role", | |
| "origin_acc": 81.0, | |
| "origin_prompt": "In the role of a syntax analyzer, examine the grammar of the provided sentence and decide if it is correct, answering with 'acceptable' for grammatically correct sentences or 'unacceptable' for incorrect ones.", | |
| "atk_acc": 75.5, | |
| "atk_prompt": "using the art of a level analyzeg, examine the grammar of the provided sentence and decide if it is genuine, answering with 'acceptable' for grammatically correct sentences or 'unacceptable' for incorrect ones. ", | |
| "transfer_ori_acc": 86.5, | |
| "transfer_atk_acc": 86.3 | |
| }, | |
| { | |
| "dataset": "mrpc", | |
| "type": "task", | |
| "origin_acc": 74.0, | |
| "origin_prompt": "Compare the following sentences and determine if they share the same semantic meaning by responding with 'equivalent' or 'not_equivalent'.", | |
| "atk_acc": 47.5, | |
| "atk_prompt": "Compare the following sentences and determine if they lack the same aspect marking by respectively with 'equivalent' or 'not_equivalent'. ", | |
| "transfer_ori_acc": 86.27450980392157, | |
| "transfer_atk_acc": 72.05882352941177 | |
| }, | |
| { | |
| "dataset": "mrpc", | |
| "type": "role", | |
| "origin_acc": 71.5, | |
| "origin_prompt": "In the role of a textual comparison specialist, examine the given sentences and decide if they share the same meaning, responding with 'equivalent' or 'not_equivalent'.", | |
| "atk_acc": 47.0, | |
| "atk_prompt": "have the role of a textual comparison academic, examine the given sentences and determine if they share the same length, responding with 'equivalent' or 'not_equivalent'. ", | |
| "transfer_ori_acc": 87.00980392156863, | |
| "transfer_atk_acc": 86.02941176470588 | |
| }, | |
| { | |
| "dataset": "qnli", | |
| "type": "task", | |
| "origin_acc": 84.0, | |
| "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": 71.0, | |
| "atk_prompt": "put the contexts and question, and be if the answer can be logically deduced from the question by stating with 'entailment' or 'not_entailment'. ", | |
| "transfer_ori_acc": 92.9, | |
| "transfer_atk_acc": 93.30000000000001 | |
| }, | |
| { | |
| "dataset": "qnli", | |
| "type": "role", | |
| "origin_acc": 84.0, | |
| "origin_prompt": "As a textual inference expert, analyze if the answer to the question can be deduced from the provided context and select 'entailment' or 'not_entailment'.", | |
| "atk_acc": 70.0, | |
| "atk_prompt": "As a structural inference expert, analyze if the answer to the challenge can be deduced from the query audience and select 'entailment' or 'not_entailment'. ", | |
| "transfer_ori_acc": 93.0, | |
| "transfer_atk_acc": 94.1 | |
| }, | |
| { | |
| "dataset": "qqp", | |
| "type": "task", | |
| "origin_acc": 82.5, | |
| "origin_prompt": "Are the following two questions equivalent or not? Answer me with \"equivalent\" or \"not_equivalent\".", | |
| "atk_acc": 78.5, | |
| "atk_prompt": "Are the following versus answers equivalent or not? Answer me with \"equivalent\" or \"not_equivalent\". ", | |
| "transfer_ori_acc": 88.5, | |
| "transfer_atk_acc": 88.5 | |
| }, | |
| { | |
| "dataset": "qqp", | |
| "type": "role", | |
| "origin_acc": 83.5, | |
| "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": 78.0, | |
| "atk_prompt": "and an instrument for question comparison analysis, consider the questions and establish if their topic is the same, responding with 'equivalent' for matching responses or 'not_equivalent' for between questions. ", | |
| "transfer_ori_acc": 89.0, | |
| "transfer_atk_acc": 90.7 | |
| }, | |
| { | |
| "dataset": "rte", | |
| "type": "task", | |
| "origin_acc": 85.0, | |
| "origin_prompt": "Review the two statements and categorize their relationship as either 'entailment' or 'not_entailment'.", | |
| "atk_acc": 59.5, | |
| "atk_prompt": "write the second statements and categorize their relationship as neither 'entailment' or 'not_entailment'. ", | |
| "transfer_ori_acc": 92.7797833935018, | |
| "transfer_atk_acc": 92.7797833935018 | |
| }, | |
| { | |
| "dataset": "rte", | |
| "type": "role", | |
| "origin_acc": 83.5, | |
| "origin_prompt": "While performing entailment analysis, classify the relationship between the provided sentences as 'entailment' or 'not_entailment'.", | |
| "atk_acc": 79.0, | |
| "atk_prompt": "was performing entailment analysis, classify the relationship between the first phrase as 'entailment' or 'not_entailment'. ", | |
| "transfer_ori_acc": 93.14079422382672, | |
| "transfer_atk_acc": 93.14079422382672 | |
| }, | |
| { | |
| "dataset": "sst2", | |
| "type": "task", | |
| "origin_acc": 95.5, | |
| "origin_prompt": "After examining the following expression, label its emotion as either 'positive' or 'negative'.", | |
| "atk_acc": 94.5, | |
| "atk_prompt": "After examining the following expression, label its emotion as either 'positive' or 'negative' Q47Jmd4lMV. ", | |
| "transfer_ori_acc": 92.77522935779817, | |
| "transfer_atk_acc": 92.66055045871559 | |
| }, | |
| { | |
| "dataset": "sst2", | |
| "type": "role", | |
| "origin_acc": 97.5, | |
| "origin_prompt": "In the capacity of a sentiment classifier, decide whether the given quote is 'positive' or 'negative'.", | |
| "atk_acc": 96.5, | |
| "atk_prompt": "In the capacity of a sentiment classifier, decide whether the given quote is 'positive' or 'negative' 9Q3S1F94fE. ", | |
| "transfer_ori_acc": 96.44495412844036, | |
| "transfer_atk_acc": 96.44495412844036 | |
| }, | |
| { | |
| "dataset": "wnli", | |
| "type": "task", | |
| "origin_acc": 69.01, | |
| "origin_prompt": "Review the two statements and categorize their relationship as either 'entailment' or 'not_entailment'.", | |
| "atk_acc": 59.15, | |
| "atk_prompt": "examine the paired actions and categorize their relationship as is 'entailment' or 'not_entailment'. ", | |
| "transfer_ori_acc": 77.46478873239437, | |
| "transfer_atk_acc": 76.05633802816901 | |
| }, | |
| { | |
| "dataset": "wnli", | |
| "type": "role", | |
| "origin_acc": 66.2, | |
| "origin_prompt": "In the role of a semantic relationship analyzer, examine the connection between the given sentences and decide if they exhibit entailment or not_entailment. Answer with 'entailment' or 'not_entailment'.", | |
| "atk_acc": 56.34, | |
| "atk_prompt": "In the role of a semantic relationship analyzer, define the connection between the given links and decide if they display entailment or not_entailment. Answer with 'entailment' or 'not_entailment'. ", | |
| "transfer_ori_acc": 76.05633802816901, | |
| "transfer_atk_acc": 76.05633802816901 | |
| }, | |
| { | |
| "dataset": "mmlu", | |
| "type": "task", | |
| "origin_acc": 66.5, | |
| "origin_prompt": "Please respond to the multiple-choice question about {} by selecting the appropriate answer: 'A', 'B', 'C', or 'D'.", | |
| "atk_acc": 11.5, | |
| "atk_prompt": "at respond to the multiple-independent question about {} by selecting the inappropriate question: 'A', 'B', 'C', or 'D'. ", | |
| "transfer_ori_acc": 53.36879432624113, | |
| "transfer_atk_acc": 14.893617021276595 | |
| }, | |
| { | |
| "dataset": "mmlu", | |
| "type": "role", | |
| "origin_acc": 65.5, | |
| "origin_prompt": "Considering your familiarity with {}, attend to the following multiple-choice question by picking 'A', 'B', 'C', or 'D'.", | |
| "atk_acc": 52.5, | |
| "atk_prompt": "all your ability with {}, attend to the following multiple-select question by picking 'A', 'B', 'C', or 'D'.", | |
| "transfer_ori_acc": 54.43262411347518, | |
| "transfer_atk_acc": 54.07801418439716 | |
| }, | |
| { | |
| "dataset": "squad_v2", | |
| "type": "task", | |
| "origin_acc": 72.25, | |
| "origin_prompt": "Based on the given context, provide the best possible answer. If there's no answer available in the context, reply with 'unanswerable'.", | |
| "atk_acc": 65.81, | |
| "atk_prompt": "Based on the use context, provide the best possible answer. who there'tis no answer provided in the area, reply with 'unanswerable'.", | |
| "transfer_ori_acc": 90.04896616541353, | |
| "transfer_atk_acc": 90.54896616541353 | |
| }, | |
| { | |
| "dataset": "squad_v2", | |
| "type": "role", | |
| "origin_acc": 72.45, | |
| "origin_prompt": "As a proficient expert in the given context, search for the most relevant answer. If the answer cannot be found, respond by saying 'unanswerable'.", | |
| "atk_acc": 61.02, | |
| "atk_prompt": "As a proficient expert in the given context, try for the most specific out. If the question lacks be search, end by as 'unanswerable'.", | |
| "transfer_ori_acc": 90.54896616541353, | |
| "transfer_atk_acc": 90.55717634603751 | |
| }, | |
| { | |
| "dataset": "iwslt", | |
| "type": "task", | |
| "origin_acc": 0.24, | |
| "origin_prompt": "Convert the following sentence from its original {} language to the target language {}.", | |
| "atk_acc": 0.21, | |
| "atk_prompt": "Convert the following sentence from its actual {} language to the net language {}. ", | |
| "transfer_ori_acc": 0.23981220411098694, | |
| "transfer_atk_acc": 0.22991007113697723 | |
| }, | |
| { | |
| "dataset": "iwslt", | |
| "type": "role", | |
| "origin_acc": 0.24, | |
| "origin_prompt": "Assuming the responsibilities of a professional translator, translate the subsequent text passage from {} to {}.", | |
| "atk_acc": 0.17, | |
| "atk_prompt": "what the responsibilities of a professional scholar, translate the subsequent text passage from {} to {}. ", | |
| "transfer_ori_acc": 0.2676477143562027, | |
| "transfer_atk_acc": 0.23524703512046088 | |
| }, | |
| { | |
| "dataset": "un_multi", | |
| "type": "task", | |
| "origin_acc": 0.36, | |
| "origin_prompt": "Translate the following text from the source language {} to the target language {}.", | |
| "atk_acc": 0.35, | |
| "atk_prompt": "Translate the following area from the standard language {} to the target language {}. ", | |
| "transfer_ori_acc": 0.35343571054545636, | |
| "transfer_atk_acc": 0.3527277831126269 | |
| }, | |
| { | |
| "dataset": "un_multi", | |
| "type": "role", | |
| "origin_acc": 0.35, | |
| "origin_prompt": "As a qualified translator, convert the given sentence from its original {} language to the target language {}.", | |
| "atk_acc": 0.26, | |
| "atk_prompt": "As a qualified proper, converts the target sentence from its original {} language to the english language {}. ", | |
| "transfer_ori_acc": 0.35395992027011125, | |
| "transfer_atk_acc": 0.35538909869030366 | |
| }, | |
| { | |
| "dataset": "math", | |
| "type": "task", | |
| "origin_acc": 22.5, | |
| "origin_prompt": "Compute the result of this math task concerning {}.", | |
| "atk_acc": 3.12, | |
| "atk_prompt": "Compute the degree of this math task concerning {}. ", | |
| "transfer_ori_acc": 16.25, | |
| "transfer_atk_acc": 14.374999999999998 | |
| }, | |
| { | |
| "dataset": "math", | |
| "type": "role", | |
| "origin_acc": 22.5, | |
| "origin_prompt": "As a mathematics instructor, calculate the answer to the following problem related to {}.", | |
| "atk_acc": 7.5, | |
| "atk_prompt": "as a mathematics instructor, evaluate the reply to the following problem and to {}. ", | |
| "transfer_ori_acc": 15.625, | |
| "transfer_atk_acc": 15.0 | |
| } | |
| ] |