Spaces:
Running
Running
[ | |
{ | |
"dataset": "cola", | |
"type": "task", | |
"origin_acc": 80.5, | |
"origin_prompt": "Examine the sentence and decide if its grammar is 'Acceptable' or 'Unacceptable'.", | |
"atk_acc": 39.5, | |
"atk_prompt": "Exams the sentence and defining if its jargon is 'Acceptable' or 'Unacceptable'. ", | |
"transfer_ori_acc": 76.3, | |
"transfer_atk_acc": 74.4 | |
}, | |
{ | |
"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": 76.0, | |
"atk_prompt": "Across the role of a syntax analyzer, examine the dictionary of the provided chastisement and decide if it is adequate, answered with 'acceptable' for grammatically correct sentences or 'unacceptable' for deceptive ones. ", | |
"transfer_ori_acc": 74.2, | |
"transfer_atk_acc": 73.3 | |
}, | |
{ | |
"dataset": "mrpc", | |
"type": "task", | |
"origin_acc": 73.0, | |
"origin_prompt": "Assess if the two given sentences have equivalent meanings by selecting 'equivalent' or 'not_equivalent'.", | |
"atk_acc": 59.0, | |
"atk_prompt": "Appraisal if the two accorded sentences enjoys equivalent connotation by choice 'equivalent' or 'not_equivalent'. ", | |
"transfer_ori_acc": 82.84313725490196, | |
"transfer_atk_acc": 83.08823529411765 | |
}, | |
{ | |
"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": 57.0, | |
"atk_prompt": "De the role of a textual comparisons scholar, revisited the given sentences and decide if they exchange the same feel, responding with 'equivalent' or 'not_equivalent'. ", | |
"transfer_ori_acc": 79.65686274509804, | |
"transfer_atk_acc": 79.16666666666666 | |
}, | |
{ | |
"dataset": "qnli", | |
"type": "task", | |
"origin_acc": 84.5, | |
"origin_prompt": "Examine the context and question, and determine if the context logically implies the answer by selecting 'entailment' or 'not_entailment'.", | |
"atk_acc": 63.5, | |
"atk_prompt": "Discuss the background and question, and determine if the framework intuitively presupposes the answer by akhtar 'entailment' or 'not_entailment'. ", | |
"transfer_ori_acc": 86.5, | |
"transfer_atk_acc": 80.30000000000001 | |
}, | |
{ | |
"dataset": "qnli", | |
"type": "role", | |
"origin_acc": 85.5, | |
"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": 68.5, | |
"atk_prompt": "Iike a textual analyst, analyze if the submitted regard rationally implies the replies to the issuing and indicates your clout with 'entailment' or 'not_entailment'. ", | |
"transfer_ori_acc": 88.8, | |
"transfer_atk_acc": 86.1 | |
}, | |
{ | |
"dataset": "qqp", | |
"type": "task", | |
"origin_acc": 83.5, | |
"origin_prompt": "Determine if the given pair of statements can be considered the same by responding with 'equivalent' or 'not_equivalent'.", | |
"atk_acc": 80.0, | |
"atk_prompt": "Determine if the given pair of representations can constitute felt the same by responding with 'equivalent' or 'not_equivalent'. ", | |
"transfer_ori_acc": 86.8, | |
"transfer_atk_acc": 86.9 | |
}, | |
{ | |
"dataset": "qqp", | |
"type": "role", | |
"origin_acc": 83.0, | |
"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": 80.0, | |
"atk_prompt": "Interim as a issues equivalence instrument, determine if the provided aspects are equivalent in meaning, answering with 'equivalent' for selfsame questions or 'not_equivalent' for dissimilar ones. ", | |
"transfer_ori_acc": 86.5, | |
"transfer_atk_acc": 86.4 | |
}, | |
{ | |
"dataset": "rte", | |
"type": "task", | |
"origin_acc": 84.5, | |
"origin_prompt": "Does the relationship between the given sentences represent entailment or not_entailment? Respond with 'entailment' or 'not_entailment'.", | |
"atk_acc": 79.5, | |
"atk_prompt": "Do the coitus between the given sentences comprised entailment or not_entailment? Meet with 'entailment' or 'not_entailment'. ", | |
"transfer_ori_acc": 83.75451263537906, | |
"transfer_atk_acc": 81.94945848375451 | |
}, | |
{ | |
"dataset": "rte", | |
"type": "role", | |
"origin_acc": 83.0, | |
"origin_prompt": "As an entailment identification system, examine the connection between the following sentences and respond with 'entailment' or 'not_entailment'.", | |
"atk_acc": 79.5, | |
"atk_prompt": "As an entailment identification system, revisited the connection between the following sentences and respondent with 'entailment' or 'not_entailment'. ", | |
"transfer_ori_acc": 82.67148014440433, | |
"transfer_atk_acc": 83.03249097472924 | |
}, | |
{ | |
"dataset": "sst2", | |
"type": "task", | |
"origin_acc": 96.0, | |
"origin_prompt": "Read the provided excerpt and choose between 'positive' and 'negative' to describe its sentiment.", | |
"atk_acc": 85.0, | |
"atk_prompt": "Lu the rendered excerpt and withheld between 'positive' and 'negative' to describe its foreboding. ", | |
"transfer_ori_acc": 94.72477064220183, | |
"transfer_atk_acc": 95.18348623853211 | |
}, | |
{ | |
"dataset": "sst2", | |
"type": "role", | |
"origin_acc": 97.5, | |
"origin_prompt": "Emulating a sentiment classification system, indicate whether the provided text is 'positive' or 'negative'.", | |
"atk_acc": 91.5, | |
"atk_prompt": "Emulating a ambience classification mechanisms, describe whether the presented writings is 'positive' or 'negative'. ", | |
"transfer_ori_acc": 94.95412844036697, | |
"transfer_atk_acc": 95.29816513761467 | |
}, | |
{ | |
"dataset": "wnli", | |
"type": "task", | |
"origin_acc": 69.01, | |
"origin_prompt": "Indicate if the connection between the following sentences is 'entailment' or 'not_entailment'.", | |
"atk_acc": 59.15, | |
"atk_prompt": "Indicate if the connection between the subsequently sentences is 'entailment' or 'not_entailment'. ", | |
"transfer_ori_acc": 64.7887323943662, | |
"transfer_atk_acc": 61.97183098591549 | |
}, | |
{ | |
"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": 57.75, | |
"atk_prompt": "In the role of a semantic contacts analyzer, analysed the connecting between the given sentences and choose if they exhibit entailment or not_entailment. Answer with 'entailment' or 'not_entailment'. ", | |
"transfer_ori_acc": 56.33802816901409, | |
"transfer_atk_acc": 54.929577464788736 | |
}, | |
{ | |
"dataset": "mmlu", | |
"type": "task", | |
"origin_acc": 67.0, | |
"origin_prompt": "Please respond to the multiple-choice question about {} by selecting the appropriate answer: 'A', 'B', 'C', or 'D'.", | |
"atk_acc": 60.0, | |
"atk_prompt": "Asking reactions to the multiple-choice question about {} by selecting the appropriate reacts: 'A', 'B', 'C', or 'D'. ", | |
"transfer_ori_acc": 45.21276595744681, | |
"transfer_atk_acc": 43.97163120567376 | |
}, | |
{ | |
"dataset": "mmlu", | |
"type": "role", | |
"origin_acc": 66.0, | |
"origin_prompt": "With your knowledge of {}, tackle the following multiple-choice question by choosing 'A', 'B', 'C', or 'D'.", | |
"atk_acc": 61.5, | |
"atk_prompt": "From your acquaintances of {}, addressing the following multiple-choice question by choosing 'A', 'B', 'C', or 'D'.", | |
"transfer_ori_acc": 46.09929078014184, | |
"transfer_atk_acc": 45.56737588652482 | |
}, | |
{ | |
"dataset": "squad_v2", | |
"type": "task", | |
"origin_acc": 72.8, | |
"origin_prompt": "Using the context, determine the most suitable answer. If the context doesn't contain the answer, write 'unanswerable'.", | |
"atk_acc": 63.67, | |
"atk_prompt": "Using the context, identifies the most suitable answer. Although the context doesn't comprise the meet, editor 'unanswerable'.", | |
"transfer_ori_acc": 87.04992770387507, | |
"transfer_atk_acc": 87.31659437054175 | |
}, | |
{ | |
"dataset": "squad_v2", | |
"type": "role", | |
"origin_acc": 71.93, | |
"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": 64.13, | |
"atk_prompt": "As a knowledge expert in the given context, find for the most relevant answering. Unless the answer cannot exist found, respond by told 'unanswerable'.", | |
"transfer_ori_acc": 87.31659437054175, | |
"transfer_atk_acc": 87.51356406751144 | |
}, | |
{ | |
"dataset": "iwslt", | |
"type": "task", | |
"origin_acc": 0.23, | |
"origin_prompt": "Given the sentence below, perform a machine translation from {} to {}.", | |
"atk_acc": 0.18, | |
"atk_prompt": "Attributed the sentence below, meet a equipments interpreters from {} to {}. ", | |
"transfer_ori_acc": 0.21292285800980326, | |
"transfer_atk_acc": 0.2153933980722541 | |
}, | |
{ | |
"dataset": "iwslt", | |
"type": "role", | |
"origin_acc": 0.24, | |
"origin_prompt": "In the role of a language expert, perform a machine translation for the provided sentence, changing it from {} to {}.", | |
"atk_acc": 0.23, | |
"atk_prompt": "Of the features of a language expert, performed a machine translation for the presented sentence, variation it from {} to {}. ", | |
"transfer_ori_acc": 0.22070346732323043, | |
"transfer_atk_acc": 0.21889644783553872 | |
}, | |
{ | |
"dataset": "un_multi", | |
"type": "task", | |
"origin_acc": 0.35, | |
"origin_prompt": "Translate the following text from the source language {} to the target language {}.", | |
"atk_acc": 0.33, | |
"atk_prompt": "Translate the following texts from the source lingo {} to the millennium phrasing {}. ", | |
"transfer_ori_acc": 0.3090347352409074, | |
"transfer_atk_acc": 0.30701960419660657 | |
}, | |
{ | |
"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": 0.34, | |
"atk_prompt": "As a nuanced translation, metamorphosis the gave sentence from its original {} terminology to the aspirations grammar {}. ", | |
"transfer_ori_acc": 0.31127691224033316, | |
"transfer_atk_acc": 0.30631346636342727 | |
}, | |
{ | |
"dataset": "math", | |
"type": "task", | |
"origin_acc": 23.75, | |
"origin_prompt": "Compute the result of this math task concerning {}.", | |
"atk_acc": 1.88, | |
"atk_prompt": "Estimate the accomplishments of this math task concerning {}. ", | |
"transfer_ori_acc": 16.25, | |
"transfer_atk_acc": 15.625 | |
}, | |
{ | |
"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": 1.88, | |
"atk_prompt": "As a computations instructor, derive the rebuttal to the following hassles links to {}. ", | |
"transfer_ori_acc": 17.5, | |
"transfer_atk_acc": 17.5 | |
} | |
] |