Spaces:
Running
Running
[ | |
{ | |
"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": 77.10000000000001, | |
"transfer_atk_acc": 74.1 | |
}, | |
{ | |
"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": 74.2, | |
"transfer_atk_acc": 74.0 | |
}, | |
{ | |
"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": 80.3921568627451, | |
"transfer_atk_acc": 81.61764705882352 | |
}, | |
{ | |
"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": 79.65686274509804, | |
"transfer_atk_acc": 76.22549019607843 | |
}, | |
{ | |
"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": 85.39999999999999, | |
"transfer_atk_acc": 78.9 | |
}, | |
{ | |
"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": 77.2, | |
"transfer_atk_acc": 82.8 | |
}, | |
{ | |
"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": 87.9, | |
"transfer_atk_acc": 87.7 | |
}, | |
{ | |
"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": 86.4, | |
"transfer_atk_acc": 86.5 | |
}, | |
{ | |
"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": 84.83754512635379, | |
"transfer_atk_acc": 84.47653429602889 | |
}, | |
{ | |
"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": 83.39350180505414, | |
"transfer_atk_acc": 83.39350180505414 | |
}, | |
{ | |
"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": 93.69266055045871, | |
"transfer_atk_acc": 93.92201834862385 | |
}, | |
{ | |
"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": 94.95412844036697, | |
"transfer_atk_acc": 94.95412844036697 | |
}, | |
{ | |
"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": 63.38028169014085, | |
"transfer_atk_acc": 66.19718309859155 | |
}, | |
{ | |
"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": 56.33802816901409, | |
"transfer_atk_acc": 66.19718309859155 | |
}, | |
{ | |
"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": 45.21276595744681, | |
"transfer_atk_acc": 33.51063829787234 | |
}, | |
{ | |
"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": 46.98581560283688, | |
"transfer_atk_acc": 45.92198581560284 | |
}, | |
{ | |
"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": 87.04992770387507, | |
"transfer_atk_acc": 87.54992770387507 | |
}, | |
{ | |
"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": 87.31659437054175, | |
"transfer_atk_acc": 87.68023073417811 | |
}, | |
{ | |
"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": 0.2240211126734209, | |
"transfer_atk_acc": 0.22296244610321242 | |
}, | |
{ | |
"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": 0.22030199520456395, | |
"transfer_atk_acc": 0.22001437607394084 | |
}, | |
{ | |
"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": 0.3090347352409074, | |
"transfer_atk_acc": 0.30893566132252137 | |
}, | |
{ | |
"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": 0.31127691224033316, | |
"transfer_atk_acc": 0.306608167162218 | |
}, | |
{ | |
"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": 16.875 | |
}, | |
{ | |
"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": 17.5, | |
"transfer_atk_acc": 16.25 | |
} | |
] |