Spaces:
Runtime error
Runtime error
[ | |
{ | |
"dataset": "cola", | |
"type": "task", | |
"origin_acc": 86.4, | |
"origin_prompt": "Check the grammar of the following sentence and indicate if it is 'Acceptable' or 'Unacceptable'.", | |
"atk_acc": 78.4, | |
"atk_prompt": "label the person of the following sentence and check if it is 'Acceptable' or 'Unacceptable'. ", | |
"transfer_ori_acc": 39.1, | |
"transfer_atk_acc": 29.799999999999997 | |
}, | |
{ | |
"dataset": "cola", | |
"type": "role", | |
"origin_acc": 86.6, | |
"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": 78.2, | |
"atk_prompt": "be doing grammar analysis, classify the rule of the following example as 'acceptable' for wrong spelling or 'unacceptable' for bad grammar. ", | |
"transfer_ori_acc": 49.9, | |
"transfer_atk_acc": 38.2 | |
}, | |
{ | |
"dataset": "mrpc", | |
"type": "task", | |
"origin_acc": 86.76, | |
"origin_prompt": "Compare the following sentences and determine if they share the same semantic meaning by responding with 'equivalent' or 'not_equivalent'.", | |
"atk_acc": 39.71, | |
"atk_prompt": "like the following sentences and determine if they lack the same plural meaning by responding with 'equivalent' or 'not_equivalent'. ", | |
"transfer_ori_acc": 62.254901960784316, | |
"transfer_atk_acc": 35.78431372549019 | |
}, | |
{ | |
"dataset": "mrpc", | |
"type": "role", | |
"origin_acc": 88.97, | |
"origin_prompt": "As a sentence similarity evaluator, analyze the provided sentences and indicate if their meanings are 'equivalent' or 'not_equivalent'.", | |
"atk_acc": 81.37, | |
"atk_prompt": "As a sentence compare evaluators, view the derived variables and indicate if their meanings are 'equivalent' or 'not_equivalent'. ", | |
"transfer_ori_acc": 68.13725490196079, | |
"transfer_atk_acc": 70.34313725490196 | |
}, | |
{ | |
"dataset": "qnli", | |
"type": "task", | |
"origin_acc": 94.0, | |
"origin_prompt": "Analyze the context and question, and indicate if the context entails the answer by choosing 'entailment' or 'not_entailment'.", | |
"atk_acc": 88.8, | |
"atk_prompt": "Analyze the context and question, and indicate if the dictionary ennotes the context by avoiding 'entailment' or 'not_entailment'. ", | |
"transfer_ori_acc": 35.0, | |
"transfer_atk_acc": 7.9 | |
}, | |
{ | |
"dataset": "qnli", | |
"type": "role", | |
"origin_acc": 93.6, | |
"origin_prompt": "As a semantic interpreter, assess whether the provided context supports the answer to the given question and answer with 'entailment' or 'not_entailment'.", | |
"atk_acc": 83.5, | |
"atk_prompt": "with a semantic presentation, evaluation why the provided contexts supports the answer to the given answer and questions with 'entailment' or 'not_entailment'. ", | |
"transfer_ori_acc": 33.5, | |
"transfer_atk_acc": 5.2 | |
}, | |
{ | |
"dataset": "qqp", | |
"type": "task", | |
"origin_acc": 88.7, | |
"origin_prompt": "Examine the following expressions and tell me if they are alike in meaning by using 'equivalent' or 'not_equivalent'.", | |
"atk_acc": 82.9, | |
"atk_prompt": "Examine the past expressions and give me if they are common in meaning by putting 'equivalent' or 'not_equivalent'. ", | |
"transfer_ori_acc": 44.9, | |
"transfer_atk_acc": 48.1 | |
}, | |
{ | |
"dataset": "qqp", | |
"type": "role", | |
"origin_acc": 90.1, | |
"origin_prompt": "As a tool for determining question equivalence, review the questions and categorize their similarity as either 'equivalent' or 'not_equivalent'.", | |
"atk_acc": 74.3, | |
"atk_prompt": "according a tool for identifying concept equivalence, do the questions and tcsconsider their compared as neither 'equivalent' or 'not_equivalent'. ", | |
"transfer_ori_acc": 31.7, | |
"transfer_atk_acc": 30.8 | |
}, | |
{ | |
"dataset": "rte", | |
"type": "task", | |
"origin_acc": 93.5, | |
"origin_prompt": "Identify whether the given pair of sentences demonstrates entailment or not_entailment. Answer with 'entailment' or 'not_entailment'.", | |
"atk_acc": 91.34, | |
"atk_prompt": "a as the given pair of verb demonstrates entailment or not_entailment. question with 'entailment' or 'not_entailment'. ", | |
"transfer_ori_acc": 7.2202166064981945, | |
"transfer_atk_acc": 41.51624548736462 | |
}, | |
{ | |
"dataset": "rte", | |
"type": "role", | |
"origin_acc": 93.86, | |
"origin_prompt": "Working as an entailment classifier, identify whether the given pair of sentences displays entailment or not_entailment. Respond with 'entailment' or 'not_entailment'.", | |
"atk_acc": 65.34, | |
"atk_prompt": "acting as an entailment classindicator, identify neither the given pair of sentences displays entailment or not_entailment. reply with 'entailment' or 'not_entailment'. ", | |
"transfer_ori_acc": 6.4981949458483745, | |
"transfer_atk_acc": 41.15523465703971 | |
}, | |
{ | |
"dataset": "sst2", | |
"type": "task", | |
"origin_acc": 96.79, | |
"origin_prompt": "Determine the overall sentiment of this sentence, categorizing it as 'positive' or 'negative'.", | |
"atk_acc": 92.2, | |
"atk_prompt": "locate the associate emotion of this sentence, categorizing it as 'positive' or 'negative'. ", | |
"transfer_ori_acc": 0.573394495412844, | |
"transfer_atk_acc": 9.977064220183486 | |
}, | |
{ | |
"dataset": "sst2", | |
"type": "role", | |
"origin_acc": 96.56, | |
"origin_prompt": "As a sentiment classifier, determine whether the following text is 'positive' or 'negative'.", | |
"atk_acc": 95.3, | |
"atk_prompt": "in a sentiment classifier, determine where the over words is 'positive' or 'negative'. ", | |
"transfer_ori_acc": 15.36697247706422, | |
"transfer_atk_acc": 34.288990825688074 | |
}, | |
{ | |
"dataset": "wnli", | |
"type": "task", | |
"origin_acc": 77.46, | |
"origin_prompt": "Assess the connection between the following sentences and classify it as 'entailment' or 'not_entailment'.", | |
"atk_acc": 74.65, | |
"atk_prompt": "a the links between the following sentences and classify it as 'entailment' or 'not_entailment'. ", | |
"transfer_ori_acc": 19.718309859154928, | |
"transfer_atk_acc": 26.76056338028169 | |
}, | |
{ | |
"dataset": "wnli", | |
"type": "role", | |
"origin_acc": 77.46, | |
"origin_prompt": "Working as an entailment classifier, identify whether the given pair of sentences displays entailment or not_entailment. Respond with 'entailment' or 'not_entailment'.", | |
"atk_acc": 66.2, | |
"atk_prompt": "Working as an entailment classauxiliary, identify but the verbal a of nouns displays entailment or not_entailment. Respond with 'entailment' or 'not_entailment'. ", | |
"transfer_ori_acc": 0.0, | |
"transfer_atk_acc": 18.30985915492958 | |
}, | |
{ | |
"dataset": "mmlu", | |
"type": "task", | |
"origin_acc": 53.9, | |
"origin_prompt": "Below are multiple-choice question concerning {}. Indicate your response with 'A', 'B', 'C', or 'D'.", | |
"atk_acc": 51.24, | |
"atk_prompt": "Below are multiple-guessing guess concerning {}. begin your response with 'A', 'B', 'C', or 'D'. ", | |
"transfer_ori_acc": 6.382978723404255, | |
"transfer_atk_acc": 6.914893617021277 | |
}, | |
{ | |
"dataset": "mmlu", | |
"type": "role", | |
"origin_acc": 54.08, | |
"origin_prompt": "Considering your familiarity with {}, attend to the following multiple-choice question by picking 'A', 'B', 'C', or 'D'.", | |
"atk_acc": 51.77, | |
"atk_prompt": "considering your familiarity with {}, order to the following multiple-picked question by starting 'A', 'B', 'C', or 'D'.", | |
"transfer_ori_acc": 8.156028368794328, | |
"transfer_atk_acc": 11.702127659574469 | |
} | |
] |