Spaces:
Runtime error
Runtime error
[ | |
{ | |
"dataset": "cola", | |
"type": "task", | |
"origin_acc": 80.5, | |
"origin_prompt": "Analyze the provided sentence and classify its grammatical correctness as 'Acceptable' or 'Unacceptable'.", | |
"atk_acc": 67.5, | |
"atk_prompt": "Analysing the provided sentences and classify its pronouns correct as 'Acceptable' or 'Unacceptable'. ", | |
"transfer_ori_acc": 10.9, | |
"transfer_atk_acc": 54.7 | |
}, | |
{ | |
"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": 77.5, | |
"atk_prompt": "In the role of a syntax checker, examine the grammɑr of the provided sentence and decide if it is correct, answering with 'acceptable' for grammatically correct sentence or 'unacceptable' for incorrect ones. ", | |
"transfer_ori_acc": 3.4000000000000004, | |
"transfer_atk_acc": 10.299999999999999 | |
}, | |
{ | |
"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": 68.0, | |
"atk_prompt": "Ass ess if the two gien sentences have equivalent meanings by selecting 'equivalent' or 'not_equivalent'. ", | |
"transfer_ori_acc": 69.36274509803921, | |
"transfer_atk_acc": 70.34313725490196 | |
}, | |
{ | |
"dataset": "mrpc", | |
"type": "role", | |
"origin_acc": 71.5, | |
"origin_prompt": "As a linguistic comparator, review the following pair of sentences and determine their semantic equivalence by choosing 'equivalent' or 'not_equivalent'.", | |
"atk_acc": 64.5, | |
"atk_prompt": "As a linguistic comparator, review the following torque of sentences and determine their semantiϲ eԛuivalence by choosing 'equivalent' or 'not_equivalent'. ", | |
"transfer_ori_acc": 61.51960784313726, | |
"transfer_atk_acc": 67.15686274509804 | |
}, | |
{ | |
"dataset": "qnli", | |
"type": "task", | |
"origin_acc": 85.0, | |
"origin_prompt": "Examine the context and question, and determine if the context logically implies the answer by selecting 'entailment' or 'not_entailment'.", | |
"atk_acc": 76.0, | |
"atk_prompt": "Examine the cntext and question, and determine if the backdrop logically implies the answer by selecting 'entailment' or 'not_entailment'. ", | |
"transfer_ori_acc": 26.900000000000002, | |
"transfer_atk_acc": 42.0 | |
}, | |
{ | |
"dataset": "qnli", | |
"type": "role", | |
"origin_acc": 83.0, | |
"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": 73.5, | |
"atk_prompt": "Aѕ a semantic researcher, evaluate si the gave framework supports the respond to the question and choose 'entailment' or 'not_entailment'. ", | |
"transfer_ori_acc": 41.6, | |
"transfer_atk_acc": 40.1 | |
}, | |
{ | |
"dataset": "qqp", | |
"type": "task", | |
"origin_acc": 82.5, | |
"origin_prompt": "Can these two statements be considered equal in meaning? Answer with 'equivalent' or 'not_equivalent'.", | |
"atk_acc": 80.0, | |
"atk_prompt": "Can these two st atements be considered equal in meaning? Ansԝer with 'equivalent' or 'not_equivalent'. ", | |
"transfer_ori_acc": 36.3, | |
"transfer_atk_acc": 31.2 | |
}, | |
{ | |
"dataset": "qqp", | |
"type": "role", | |
"origin_acc": 82.5, | |
"origin_prompt": "In the capacity of a question assessment system, indicate if the meaning of the provided questions is the same, responding with 'equivalent' or 'not_equivalent'.", | |
"atk_acc": 80.5, | |
"atk_prompt": "In the abilities of a question ɑssessment system, indicate if the meaning of the provided matters is the same, responding with 'equivalent' or 'not_equivalent'. ", | |
"transfer_ori_acc": 46.9, | |
"transfer_atk_acc": 40.5 | |
}, | |
{ | |
"dataset": "rte", | |
"type": "task", | |
"origin_acc": 84.0, | |
"origin_prompt": "Review the two statements and categorize their relationship as either 'entailment' or 'not_entailment'.", | |
"atk_acc": 76.5, | |
"atk_prompt": "Review the two declarations and categorize their relationship as neither 'entailment' or 'not_entailment'. ", | |
"transfer_ori_acc": 50.54151624548736, | |
"transfer_atk_acc": 45.84837545126354 | |
}, | |
{ | |
"dataset": "rte", | |
"type": "role", | |
"origin_acc": 83.5, | |
"origin_prompt": "As an entailment identification system, examine the connection between the following sentences and respond with 'entailment' or 'not_entailment'.", | |
"atk_acc": 80.0, | |
"atk_prompt": "As an entailment identification system, eamine the connection between the following sentences and reѕpond with 'entailment' or 'not_entailment'. ", | |
"transfer_ori_acc": 46.20938628158845, | |
"transfer_atk_acc": 47.292418772563174 | |
}, | |
{ | |
"dataset": "sst2", | |
"type": "task", | |
"origin_acc": 95.5, | |
"origin_prompt": "After examining the following expression, label its emotion as either 'positive' or 'negative'.", | |
"atk_acc": 74.0, | |
"atk_prompt": "Ater examining the following expression, etiquette its emotion as nor 'positive' or 'negative'. ", | |
"transfer_ori_acc": 7.912844036697248, | |
"transfer_atk_acc": 5.045871559633028 | |
}, | |
{ | |
"dataset": "sst2", | |
"type": "role", | |
"origin_acc": 97.5, | |
"origin_prompt": "In the capacity of a sentiment classifier, decide whether the given quote is 'positive' or 'negative'.", | |
"atk_acc": 93.5, | |
"atk_prompt": "Onto the capacity of a feeling classifeir, decide si the given quote is 'positive' or 'negative'. ", | |
"transfer_ori_acc": 20.18348623853211, | |
"transfer_atk_acc": 0.8027522935779817 | |
}, | |
{ | |
"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": 61.97, | |
"atk_prompt": "Indicate if the connection between the following sentences is 'entailment' or 'not_entailment' Vq3aBzuZcD. ", | |
"transfer_ori_acc": 9.859154929577464, | |
"transfer_atk_acc": 18.30985915492958 | |
}, | |
{ | |
"dataset": "wnli", | |
"type": "role", | |
"origin_acc": 66.2, | |
"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": 59.15, | |
"atk_prompt": "In your role as an entailment analysis tool, assess the relationship between the given sentences and classify it as 'entailment' or 'not_entailment' is77sOXAu8. ", | |
"transfer_ori_acc": 23.943661971830984, | |
"transfer_atk_acc": 8.450704225352112 | |
}, | |
{ | |
"dataset": "mmlu", | |
"type": "task", | |
"origin_acc": 67.5, | |
"origin_prompt": "In relation to the multiple-choice question on {}, please provide the accurate answer by choosing 'A', 'B', 'C', or 'D'.", | |
"atk_acc": 61.5, | |
"atk_prompt": "At relationship to the mul𝚝iple-choice question on {}, please proviԁe the accurate responding by choosing 'A', 'B', 'C', or 'D'. ", | |
"transfer_ori_acc": 9.397163120567376, | |
"transfer_atk_acc": 4.432624113475177 | |
}, | |
{ | |
"dataset": "mmlu", | |
"type": "role", | |
"origin_acc": 65.5, | |
"origin_prompt": "As someone well-versed in {}, please address the multiple-choice question below by selecting 'A', 'B', 'C', or 'D'.", | |
"atk_acc": 61.5, | |
"atk_prompt": "As someone well-vesred in {}, please address the muⅼtiple-choice questioո below by selecting 'A', 'B', 'C', or 'D'.", | |
"transfer_ori_acc": 8.51063829787234, | |
"transfer_atk_acc": 10.815602836879433 | |
} | |
] |