Spaces:
Running
Running
[ | |
{ | |
"dataset": "cola", | |
"type": "task", | |
"origin_acc": 77.9, | |
"origin_prompt": "Examine the given sentence and decide if it is grammatically sound. Answer with either 'Acceptable' or 'Unacceptable':", | |
"atk_acc": 31.1, | |
"atk_prompt": "Exapine the gievn sentene and dVecide if it is grammktically sound. Answer with either 'Acceptable' or 'Unacceptable':", | |
"transfer_ori_acc": 50.0, | |
"transfer_atk_acc": 54.1 | |
}, | |
{ | |
"dataset": "cola", | |
"type": "role", | |
"origin_acc": 76.3, | |
"origin_prompt": "As an instrument for grammar evaluation, consider the sentence and determine if its grammar is correct, responding with 'acceptable' for correct grammar or 'unacceptable' for incorrect grammar:", | |
"atk_acc": 36.5, | |
"atk_prompt": "sA an instrument for grammar evaluatiJn, cnsider the setnence and deterbmine if its grmamar is crorect, reYponding with 'acceptable' for corect gramOar or 'unacceptable' for incorGect rgammar:", | |
"transfer_ori_acc": 36.199999999999996, | |
"transfer_atk_acc": 36.8 | |
}, | |
{ | |
"dataset": "mrpc", | |
"type": "task", | |
"origin_acc": 82.35, | |
"origin_prompt": "Compare the following sentences and determine if they share the same semantic meaning by responding with 'equivalent' or 'not_equivalent'.", | |
"atk_acc": 76.96, | |
"atk_prompt": "Compar the folhowing sentences and deWermine if they share the same semantic emaning by respondig with 'equivalent' or 'not_equivalent'. ", | |
"transfer_ori_acc": 67.40196078431373, | |
"transfer_atk_acc": 57.107843137254896 | |
}, | |
{ | |
"dataset": "mrpc", | |
"type": "role", | |
"origin_acc": 82.6, | |
"origin_prompt": "In your capacity as a semantic comparison tool, examine the given sentences and decide if their meanings are identical, responding with 'equivalent' or 'not_equivalent'.", | |
"atk_acc": 62.25, | |
"atk_prompt": "In your capacity as a seantic coGparison tolo, exaine the given esentences and decide if their meanings are identiacl, resYonding with 'equivalent' or 'not_equivalent'. ", | |
"transfer_ori_acc": 64.2156862745098, | |
"transfer_atk_acc": 14.950980392156863 | |
}, | |
{ | |
"dataset": "qnli", | |
"type": "task", | |
"origin_acc": 89.8, | |
"origin_prompt": "Evaluate whether the given context supports the answer to the question by responding with 'entailment' or 'not_entailment'.", | |
"atk_acc": 38.6, | |
"atk_prompt": "Evlauate whyther the giGven cotext supporzs the answeQ to the quePtion by rseponding with 'entailment' or 'not_entailment'. ", | |
"transfer_ori_acc": 26.5, | |
"transfer_atk_acc": 17.2 | |
}, | |
{ | |
"dataset": "qnli", | |
"type": "role", | |
"origin_acc": 89.4, | |
"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": 2.1, | |
"atk_prompt": "sA a esmantic interpreter, aBssess whehter the proviedd contexYt spuports the answher to the gEven questin and answOr with 'entailment' or 'not_entailment'. ", | |
"transfer_ori_acc": 8.7, | |
"transfer_atk_acc": 8.6 | |
}, | |
{ | |
"dataset": "qqp", | |
"type": "task", | |
"origin_acc": 87.8, | |
"origin_prompt": "Can these two statements be considered equal in meaning? Answer with 'equivalent' or 'not_equivalent'.", | |
"atk_acc": 59.8, | |
"atk_prompt": "Can these tow statYements be cnosidered qeual in maening? AnsweI with 'equivalent' or 'not_equivalent'. ", | |
"transfer_ori_acc": 22.900000000000002, | |
"transfer_atk_acc": 17.2 | |
}, | |
{ | |
"dataset": "qqp", | |
"type": "role", | |
"origin_acc": 86.9, | |
"origin_prompt": "Functioning as a question similarity evaluation tool, analyze the given questions and decide if they share the same meaning, responding with 'equivalent' or 'not_equivalent'.", | |
"atk_acc": 81.4, | |
"atk_prompt": "Functioning as a question smiilarity eavluation toXl, analyze the givYen questions and decidae if they share the same meajning, responding with 'equivalent' or 'not_equivalent'. ", | |
"transfer_ori_acc": 14.6, | |
"transfer_atk_acc": 10.4 | |
}, | |
{ | |
"dataset": "rte", | |
"type": "task", | |
"origin_acc": 86.64, | |
"origin_prompt": "Are the following two sentences entailment or not_entailment? Answer me with \"entailment\" or \"not_entailment\", just one word.", | |
"atk_acc": 81.95, | |
"atk_prompt": "Aer the following two Ysentences entailment or not_entailment? nswer me with \"entailment\" or \"not_entailment\", just one word. ", | |
"transfer_ori_acc": 27.075812274368232, | |
"transfer_atk_acc": 14.079422382671481 | |
}, | |
{ | |
"dataset": "rte", | |
"type": "role", | |
"origin_acc": 84.84, | |
"origin_prompt": "While performing entailment analysis, classify the relationship between the provided sentences as 'entailment' or 'not_entailment':", | |
"atk_acc": 82.67, | |
"atk_prompt": "While performing entailment analysis, cassify the reiationship between the proviLded sentences as 'entailment' or 'not_entailment':", | |
"transfer_ori_acc": 23.104693140794225, | |
"transfer_atk_acc": 18.4115523465704 | |
}, | |
{ | |
"dataset": "sst2", | |
"type": "task", | |
"origin_acc": 94.84, | |
"origin_prompt": "Analyze the tone of this statement and respond with either 'positive' or 'negative':", | |
"atk_acc": 94.04, | |
"atk_prompt": "Analze the tone of this sattement and respond with either 'positive' or 'negative': ", | |
"transfer_ori_acc": 47.935779816513765, | |
"transfer_atk_acc": 47.706422018348626 | |
}, | |
{ | |
"dataset": "sst2", | |
"type": "role", | |
"origin_acc": 95.3, | |
"origin_prompt": "Serving as a sentiment evaluation model, determine if the given statement is 'positive' or 'negative'. Classify:", | |
"atk_acc": 64.91, | |
"atk_prompt": "Servign as a sentimBnt envaluation model, Qetermine if the Iiven statemen is 'positive' or 'negative'. Classhfy: ", | |
"transfer_ori_acc": 26.261467889908257, | |
"transfer_atk_acc": 48.96788990825688 | |
}, | |
{ | |
"dataset": "wnli", | |
"type": "task", | |
"origin_acc": 66.2, | |
"origin_prompt": "Are the following two sentences entailment or not_entailment? Answer me with \"entailment\" or \"not_entailment\", just one word.", | |
"atk_acc": 60.56, | |
"atk_prompt": "Are the follHwing Ntwo sentences entailment or not_entailment? Answer me with \"entailment\" or \"not_entailment\", just one wor. ", | |
"transfer_ori_acc": 25.352112676056336, | |
"transfer_atk_acc": 23.943661971830984 | |
}, | |
{ | |
"dataset": "wnli", | |
"type": "role", | |
"origin_acc": 66.2, | |
"origin_prompt": "As an entailment identification system, examine the connection between the following sentences and respond with 'entailment' or 'not_entailment':", | |
"atk_acc": 57.75, | |
"atk_prompt": "As an entailment identfiication zystem, examine the connection between the flolowing sentences and respond with 'entailment' or 'not_entailment':", | |
"transfer_ori_acc": 43.66197183098591, | |
"transfer_atk_acc": 38.028169014084504 | |
}, | |
{ | |
"dataset": "mmlu", | |
"type": "task", | |
"origin_acc": 45.74, | |
"origin_prompt": "For each multiple-choice question about {}, identify the correct answer by selecting 'A', 'B', 'C', or 'D'.", | |
"atk_acc": 42.2, | |
"atk_prompt": "For each multiple-chotce question about {}, dentify the caorrect answedr by selccting 'A', 'B', 'C', or 'D'. ", | |
"transfer_ori_acc": 22.69503546099291, | |
"transfer_atk_acc": 19.326241134751772 | |
}, | |
{ | |
"dataset": "mmlu", | |
"type": "role", | |
"origin_acc": 44.86, | |
"origin_prompt": "Utilizing your expertise in {}, answer the following multiple-choice question by picking 'A', 'B', 'C', or 'D'.", | |
"atk_acc": 41.13, | |
"atk_prompt": "Utilizing your expertise in {}, ansKer the following multiprle-choice question by ipcking 'A', 'B', 'C', or 'D'.", | |
"transfer_ori_acc": 20.74468085106383, | |
"transfer_atk_acc": 23.93617021276596 | |
} | |
] |