Spaces:
Runtime error
Runtime error
[ | |
{ | |
"dataset": "cola", | |
"type": "task", | |
"origin_acc": 86.2, | |
"origin_prompt": "Assess the following sentence and determine if it is grammatically correct. Respond with 'Acceptable' or 'Unacceptable':", | |
"atk_acc": 78.7, | |
"atk_prompt": "Assess the following sentence and identify if it is pronouns cоrrect. Replying with 'Acceptable' or 'Unacceptable':", | |
"transfer_ori_acc": 69.0, | |
"transfer_atk_acc": 67.4 | |
}, | |
{ | |
"dataset": "cola", | |
"type": "role", | |
"origin_acc": 86.0, | |
"origin_prompt": "As a grammar identification system, examine the provided sentence and respond with 'acceptable' for grammatically correct sentences or 'unacceptable' for incorrect ones:", | |
"atk_acc": 81.0, | |
"atk_prompt": "Aѕ a grammar identificatiоn systems, examine the provided sentence and respoոd with 'acceptable' for pronouns rightness sentence or 'unacceptable' for incorrect those:", | |
"transfer_ori_acc": 9.6, | |
"transfer_atk_acc": 22.2 | |
}, | |
{ | |
"dataset": "mrpc", | |
"type": "task", | |
"origin_acc": 86.76, | |
"origin_prompt": "Please analyze the provided sentences and indicate if their meanings are the same by choosing 'equivalent' or 'not_equivalent'.", | |
"atk_acc": 83.09, | |
"atk_prompt": "Invited analyze the provideԁ verdicts and indicate if their meanings are the same by selecting 'equivalent' or 'not_equivalent'. ", | |
"transfer_ori_acc": 54.166666666666664, | |
"transfer_atk_acc": 12.009803921568627 | |
}, | |
{ | |
"dataset": "mrpc", | |
"type": "role", | |
"origin_acc": 87.99, | |
"origin_prompt": "In your capacity as a language analyst, assess the following sentences and classify their similarity as 'equivalent' or 'not_equivalent'.", | |
"atk_acc": 81.13, | |
"atk_prompt": "In your capacity as a linguistics aոalyst, evaluate the following sentences and classify their metaphor as 'equivalent' or 'not_equivalent'. ", | |
"transfer_ori_acc": 51.225490196078425, | |
"transfer_atk_acc": 26.225490196078432 | |
}, | |
{ | |
"dataset": "qnli", | |
"type": "task", | |
"origin_acc": 94.1, | |
"origin_prompt": "Evaluate whether the given context supports the answer to the question by responding with 'entailment' or 'not_entailment'.", | |
"atk_acc": 93.3, | |
"atk_prompt": "Evaluate whetheⲅ the given context favours the answer to the question by responding with 'entailment' or 'not_entailment'. ", | |
"transfer_ori_acc": 26.5, | |
"transfer_atk_acc": 2.6 | |
}, | |
{ | |
"dataset": "qnli", | |
"type": "role", | |
"origin_acc": 94.2, | |
"origin_prompt": "In your role as a linguistic investigator, determine if the context given entails the answer to the question and provide your conclusion with 'entailment' or 'not_entailment'.", | |
"atk_acc": 93.1, | |
"atk_prompt": "In your role as a linguistic searchers, ԁetermine if the context awarded presupposes the answer to the questions and provide your conclusions with 'entailment' or 'not_entailment'. ", | |
"transfer_ori_acc": 31.5, | |
"transfer_atk_acc": 19.2 | |
}, | |
{ | |
"dataset": "qqp", | |
"type": "task", | |
"origin_acc": 88.3, | |
"origin_prompt": "Do these two sentences convey the same meaning? Indicate with 'equivalent' or 'not_equivalent'.", | |
"atk_acc": 86.4, | |
"atk_prompt": "Do these two verdicts convey the same connotation? Denotes with 'equivalent' or 'not_equivalent'. ", | |
"transfer_ori_acc": 28.7, | |
"transfer_atk_acc": 18.7 | |
}, | |
{ | |
"dataset": "qqp", | |
"type": "role", | |
"origin_acc": 88.5, | |
"origin_prompt": "As a tool for determining question equivalence, review the questions and categorize their similarity as either 'equivalent' or 'not_equivalent'.", | |
"atk_acc": 78.2, | |
"atk_prompt": "As a tool for deciding question equivalence, review the problems and categorize their metaphor as neither 'equivalent' or 'not_equivalent'. ", | |
"transfer_ori_acc": 8.200000000000001, | |
"transfer_atk_acc": 9.6 | |
}, | |
{ | |
"dataset": "rte", | |
"type": "task", | |
"origin_acc": 94.22, | |
"origin_prompt": "Are the following two sentences entailment or not_entailment? Answer me with \"entailment\" or \"not_entailment\", just one word.", | |
"atk_acc": 89.89, | |
"atk_prompt": "Are the subsequent secondly sentencing entailment or not_entailment? Answer me with \"entailment\" or \"not_entailment\", just one word. ", | |
"transfer_ori_acc": 27.075812274368232, | |
"transfer_atk_acc": 10.830324909747292 | |
}, | |
{ | |
"dataset": "rte", | |
"type": "role", | |
"origin_acc": 93.86, | |
"origin_prompt": "In your role as an entailment analysis tool, assess the relationship between the given sentences and classify it as 'entailment' or 'not_entailment':", | |
"atk_acc": 90.25, | |
"atk_prompt": "Throughout your role as an entailment analysis instrument, assess the relationship between the given punishments and classify it as 'entailment' or 'not_entailment':", | |
"transfer_ori_acc": 44.04332129963899, | |
"transfer_atk_acc": 14.079422382671481 | |
}, | |
{ | |
"dataset": "sst2", | |
"type": "task", | |
"origin_acc": 96.44, | |
"origin_prompt": "Analyze the tone of this statement and respond with either 'positive' or 'negative':", | |
"atk_acc": 95.76, | |
"atk_prompt": "Analysis the tone of this speeches and respond with or 'positive' or 'negative': ", | |
"transfer_ori_acc": 47.935779816513765, | |
"transfer_atk_acc": 13.073394495412844 | |
}, | |
{ | |
"dataset": "sst2", | |
"type": "role", | |
"origin_acc": 96.33, | |
"origin_prompt": "As a sentiment classifier, determine whether the following text is 'positive' or 'negative'. Please classify:", | |
"atk_acc": 93.92, | |
"atk_prompt": "Aѕ a emotion classifier, determine whether the follow ing text is 'positive' or 'negative'. Inviting classify: ", | |
"transfer_ori_acc": 33.94495412844037, | |
"transfer_atk_acc": 40.825688073394495 | |
}, | |
{ | |
"dataset": "wnli", | |
"type": "task", | |
"origin_acc": 78.87, | |
"origin_prompt": "Are the following two sentences entailment or not_entailment? Answer me with \"entailment\" or \"not_entailment\", just one word.", | |
"atk_acc": 74.65, | |
"atk_prompt": "Are the flolowing two sentences entailment or not_entailment? Answer me with \"entailment\" or \"not_entailment\", just one adjective. ", | |
"transfer_ori_acc": 25.352112676056336, | |
"transfer_atk_acc": 4.225352112676056 | |
}, | |
{ | |
"dataset": "wnli", | |
"type": "role", | |
"origin_acc": 80.28, | |
"origin_prompt": "Functioning as an entailment evaluation tool, analyze the provided sentences and decide if their relationship is 'entailment' or 'not_entailment':", | |
"atk_acc": 74.65, | |
"atk_prompt": "Functioոing as an entailment evaluation tool, analyze the provided sentences and decіde if their rapport is 'entailment' or 'not_entailment':", | |
"transfer_ori_acc": 43.66197183098591, | |
"transfer_atk_acc": 5.633802816901409 | |
}, | |
{ | |
"dataset": "mmlu", | |
"type": "task", | |
"origin_acc": 52.84, | |
"origin_prompt": "For the multiple-choice question related to {}, please choose the most accurate answer from 'A', 'B', 'C', or 'D'.", | |
"atk_acc": 51.24, | |
"atk_prompt": "In the multiple-choice question rel ated to {}, inviting choose the most accurate answer from 'A', 'B', 'C', or 'D'. ", | |
"transfer_ori_acc": 18.79432624113475, | |
"transfer_atk_acc": 20.56737588652482 | |
}, | |
{ | |
"dataset": "mmlu", | |
"type": "role", | |
"origin_acc": 53.19, | |
"origin_prompt": "As a knowledgeable individual in {}, provide your response to the multiple-choice question by choosing 'A', 'B', 'C', or 'D'.", | |
"atk_acc": 51.24, | |
"atk_prompt": "As a knowledgeable indiivdual in {}, provide your replies to the multiple-choice problem by choosing 'A', 'B', 'C', or 'D'.", | |
"transfer_ori_acc": 22.69503546099291, | |
"transfer_atk_acc": 23.04964539007092 | |
} | |
] |