Spaces:
Running
Running
[ | |
{ | |
"dataset": "cola", | |
"type": "task", | |
"origin_acc": 85.9, | |
"origin_prompt": "Determine if the grammar of the given sentence is 'Acceptable' or 'Unacceptable':", | |
"atk_acc": 78.1, | |
"atk_prompt": "Determinqe if the grmamar of the igven sentewnce is 'Acceptable' or 'Unacceptable':", | |
"transfer_ori_acc": 36.4, | |
"transfer_atk_acc": 44.7 | |
}, | |
{ | |
"dataset": "cola", | |
"type": "role", | |
"origin_acc": 86.1, | |
"origin_prompt": "In your role as a grammar check tool, assess the following sentence and classify it as 'acceptable' if it is grammatically correct or 'unacceptable' if it is incorrect:", | |
"atk_acc": 84.5, | |
"atk_prompt": "In your role as a grammar check too, assess the following senttence and classify it as 'acceptable' if it is rgammatically correct or 'unacceptable' if it is incorroct:", | |
"transfer_ori_acc": 43.1, | |
"transfer_atk_acc": 3.8 | |
}, | |
{ | |
"dataset": "mrpc", | |
"type": "task", | |
"origin_acc": 87.25, | |
"origin_prompt": "Can the given sentences be considered semantically identical? Please reply with 'equivalent' or 'not_equivalent'.", | |
"atk_acc": 83.58, | |
"atk_prompt": "Can the given sentences be consiedred semantically idePntical? Plaese reply with 'equivalent' or 'not_equivalent'. ", | |
"transfer_ori_acc": 53.431372549019606, | |
"transfer_atk_acc": 57.59803921568627 | |
}, | |
{ | |
"dataset": "mrpc", | |
"type": "role", | |
"origin_acc": 88.73, | |
"origin_prompt": "As a sentence similarity evaluator, analyze the provided sentences and indicate if their meanings are 'equivalent' or 'not_equivalent'.", | |
"atk_acc": 81.13, | |
"atk_prompt": "A a sentWnce sidmilarity evaluator, analyze the provAded sentences and idnicate if their meanVngs are 'equivalent' or 'not_equivalent'. ", | |
"transfer_ori_acc": 25.98039215686275, | |
"transfer_atk_acc": 31.372549019607842 | |
}, | |
{ | |
"dataset": "qnli", | |
"type": "task", | |
"origin_acc": 94.0, | |
"origin_prompt": "Given the question and context provided, determine if the answer can be inferred by choosing 'entailment' or 'not_entailment'.", | |
"atk_acc": 93.8, | |
"atk_prompt": "Given the question and context provided, deermine if the answer can be inferred by choosing 'entailment' or 'not_entailment'. ", | |
"transfer_ori_acc": 17.1, | |
"transfer_atk_acc": 13.700000000000001 | |
}, | |
{ | |
"dataset": "qnli", | |
"type": "role", | |
"origin_acc": 94.2, | |
"origin_prompt": "As a semantic researcher, evaluate whether the provided context supports the answer to the question and choose 'entailment' or 'not_entailment'.", | |
"atk_acc": 93.3, | |
"atk_prompt": "us a sAmantic researJcher, evZluate hwether the provided context suports the answer to the question and choose 'entailment' or 'not_entailment'. ", | |
"transfer_ori_acc": 13.4, | |
"transfer_atk_acc": 10.6 | |
}, | |
{ | |
"dataset": "qqp", | |
"type": "task", | |
"origin_acc": 88.2, | |
"origin_prompt": "Please indicate if the following pair of sentences share the same meaning by responding with 'equivalent' or 'not_equivalent'.", | |
"atk_acc": 87.4, | |
"atk_prompt": "qPlease indicate if the folloing pair of senFences share the same meaning by resopnding with 'equivalent' or 'not_equivalent'. ", | |
"transfer_ori_acc": 31.8, | |
"transfer_atk_acc": 18.099999999999998 | |
}, | |
{ | |
"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": 87.3, | |
"atk_prompt": "As a tool for determining question equivalence, review the questions and ategorize their similvarity as eitehr 'equivalent' or 'not_equivalent'. ", | |
"transfer_ori_acc": 8.200000000000001, | |
"transfer_atk_acc": 4.2 | |
}, | |
{ | |
"dataset": "rte", | |
"type": "task", | |
"origin_acc": 94.22, | |
"origin_prompt": "Examine the pair of sentences and determine if they exhibit entailment or not_entailment. Answer with either 'entailment' or 'not_entailment'.", | |
"atk_acc": 92.06, | |
"atk_prompt": "Examine the pir of sentencs and determine if they exxibit entailment or not_entailment. Answer with eitfer 'entailment' or 'not_entailment'.", | |
"transfer_ori_acc": 27.79783393501805, | |
"transfer_atk_acc": 21.660649819494584 | |
}, | |
{ | |
"dataset": "rte", | |
"type": "role", | |
"origin_acc": 93.86, | |
"origin_prompt": "As an instrument for entailment evaluation, consider the two sentences and determine if their relationship is 'entailment' or 'not_entailment'. Respond with 'entailment' or 'not_entailment':", | |
"atk_acc": 92.78, | |
"atk_prompt": "As an instrument for entailment evaluation, consider the two sentences and determine if their relationship is 'entailment' or 'not_entailment'. Respodn with 'entailment' or 'not_entailment':", | |
"transfer_ori_acc": 24.90974729241877, | |
"transfer_atk_acc": 32.851985559566785 | |
}, | |
{ | |
"dataset": "sst2", | |
"type": "task", | |
"origin_acc": 96.56, | |
"origin_prompt": "Analyze the tone of this statement and respond with either 'positive' or 'negative':", | |
"atk_acc": 95.64, | |
"atk_prompt": "AnalyVe the tone of this statelent and resBond with etiher 'positive' or 'negative': ", | |
"transfer_ori_acc": 47.935779816513765, | |
"transfer_atk_acc": 8.486238532110093 | |
}, | |
{ | |
"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": 95.76, | |
"atk_prompt": "s a sentiment classifier, determine whether the following text is 'positive' or 'negative'. Please claSsify: ", | |
"transfer_ori_acc": 33.94495412844037, | |
"transfer_atk_acc": 25.688073394495415 | |
}, | |
{ | |
"dataset": "wnli", | |
"type": "task", | |
"origin_acc": 80.28, | |
"origin_prompt": "Assess the connection between the following sentences and classify it as 'entailment' or 'not_entailment'.", | |
"atk_acc": 76.06, | |
"atk_prompt": "Nssess the connection between the fnollowing sentences and classify it as 'entailment' or 'not_entailment'.", | |
"transfer_ori_acc": 38.028169014084504, | |
"transfer_atk_acc": 29.577464788732392 | |
}, | |
{ | |
"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": 76.06, | |
"atk_prompt": "Functioning as an entailment ealuation tCol, aSalyze the provided sentences and decide if their relationship is 'entailment' or 'not_entailment':", | |
"transfer_ori_acc": 43.66197183098591, | |
"transfer_atk_acc": 40.845070422535215 | |
}, | |
{ | |
"dataset": "mmlu", | |
"type": "task", | |
"origin_acc": 52.84, | |
"origin_prompt": "Please respond to the multiple-choice question about {} by selecting the appropriate answer: 'A', 'B', 'C', or 'D'.", | |
"atk_acc": 51.95, | |
"atk_prompt": "Pqlease respond to the multiple-choice question about {} by Aelecting the appropriate answer: 'A', 'B', 'C', or 'D'. ", | |
"transfer_ori_acc": 19.148936170212767, | |
"transfer_atk_acc": 17.907801418439718 | |
}, | |
{ | |
"dataset": "mmlu", | |
"type": "role", | |
"origin_acc": 53.19, | |
"origin_prompt": "As an expert in {}, respond to the following multiple-choice question by selecting 'A', 'B', 'C', or 'D'.", | |
"atk_acc": 51.77, | |
"atk_prompt": "As an exert in {}, respond to the following multiple-choice question by selecting 'A', 'B', 'C', or 'D'.", | |
"transfer_ori_acc": 23.04964539007092, | |
"transfer_atk_acc": 24.645390070921984 | |
} | |
] |