Spaces:
Runtime error
Runtime error
[ | |
{ | |
"dataset": "cola", | |
"type": "task", | |
"origin_acc": 62.2, | |
"origin_prompt": "Assess the grammatical structure of the given sentence and classify it as 'Acceptable' or 'Unacceptable'.", | |
"atk_acc": 3.8, | |
"atk_prompt": "Assess the context t of the of sentence and judge it as 'Acceptable' or 'Unacceptable'. ", | |
"transfer_ori_acc": 86.2, | |
"transfer_atk_acc": 84.2 | |
}, | |
{ | |
"dataset": "cola", | |
"type": "role", | |
"origin_acc": 49.6, | |
"origin_prompt": "As a tool for determining grammatical correctness, review the sentence and categorize its grammar as either 'acceptable' or 'unacceptable'.", | |
"atk_acc": 0.0, | |
"atk_prompt": "should a be for calculating adjective correctness, review the sentence and categorize its i as or 'acceptable' or 'unacceptable'. ", | |
"transfer_ori_acc": 85.6, | |
"transfer_atk_acc": 85.0 | |
}, | |
{ | |
"dataset": "mrpc", | |
"type": "task", | |
"origin_acc": 69.36, | |
"origin_prompt": "Determine if the meanings of the following sentences are semantically equivalent by responding with 'equivalent' or 'not_equivalent'.", | |
"atk_acc": 33.33, | |
"atk_prompt": "Determine if the words of the following sentence are semanticdouble equivalent by thinking with 'equivalent' or 'not_equivalent'. ", | |
"transfer_ori_acc": 84.55882352941177, | |
"transfer_atk_acc": 83.82352941176471 | |
}, | |
{ | |
"dataset": "mrpc", | |
"type": "role", | |
"origin_acc": 68.14, | |
"origin_prompt": "In the role of a sentence comparison analyst, assess the provided sentences and indicate if they convey the same meaning by selecting 'equivalent' or 'not_equivalent'.", | |
"atk_acc": 17.16, | |
"atk_prompt": "to the role of a face comparison instance, assess the following sentences and indicate if they describe the same person by selecting 'equivalent' or 'not_equivalent'. ", | |
"transfer_ori_acc": 86.27450980392157, | |
"transfer_atk_acc": 85.7843137254902 | |
}, | |
{ | |
"dataset": "qnli", | |
"type": "task", | |
"origin_acc": 41.2, | |
"origin_prompt": "Based on the information in the context, decide if the answer to the question is justified by choosing 'entailment' or 'not_entailment'.", | |
"atk_acc": 0.0, | |
"atk_prompt": "Based on the information in the context, decide if the answer to the is is committed by versus 'entailment' or 'not_entailment'. ", | |
"transfer_ori_acc": 93.8, | |
"transfer_atk_acc": 93.89999999999999 | |
}, | |
{ | |
"dataset": "qnli", | |
"type": "role", | |
"origin_acc": 35.5, | |
"origin_prompt": "As a textual inference expert, analyze if the answer to the question can be deduced from the provided context and select 'entailment' or 'not_entailment'.", | |
"atk_acc": 0.0, | |
"atk_prompt": "As a textual inference expert, write if the answer to the task can be deduced from the supplied instance and search 'entailment' or 'not_entailment'. ", | |
"transfer_ori_acc": 93.0, | |
"transfer_atk_acc": 93.60000000000001 | |
}, | |
{ | |
"dataset": "qqp", | |
"type": "task", | |
"origin_acc": 41.8, | |
"origin_prompt": "Do the following expressions mean the same thing? Provide your answer as 'equivalent' or 'not_equivalent'.", | |
"atk_acc": 10.3, | |
"atk_prompt": "are the following expression do the same as? substitute your subject as 'equivalent' or 'not_equivalent'. ", | |
"transfer_ori_acc": 88.1, | |
"transfer_atk_acc": 88.0 | |
}, | |
{ | |
"dataset": "qqp", | |
"type": "role", | |
"origin_acc": 33.0, | |
"origin_prompt": "In the role of a question similarity analyzer, examine the meaning of the provided questions and decide if they are equivalent, answering with 'equivalent' for equivalent questions or 'not_equivalent' for different questions.", | |
"atk_acc": 8.2, | |
"atk_prompt": "In the role of a topic similarities analyzer, examining the semantic of the questions the and decide if they are equivalent, answer with 'equivalent' for equivalent numbers or 'not_equivalent' for various respondents. ", | |
"transfer_ori_acc": 88.1, | |
"transfer_atk_acc": 88.3 | |
}, | |
{ | |
"dataset": "rte", | |
"type": "task", | |
"origin_acc": 50.54, | |
"origin_prompt": "Are the following two sentences entailment or not_entailment? Answer me with \"entailment\" or \"not_entailment\", just one word.", | |
"atk_acc": 1.08, | |
"atk_prompt": "pair the following opposite sentences entailment or not_entailment? answers me with \"entailment\" or \"not_entailment\", just 1 word. ", | |
"transfer_ori_acc": 93.14079422382672, | |
"transfer_atk_acc": 93.14079422382672 | |
}, | |
{ | |
"dataset": "rte", | |
"type": "role", | |
"origin_acc": 36.82, | |
"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": 0.0, | |
"atk_prompt": "In the role of a descriptive relationship analyzeing, read the connection between the given sentences and learn if they exhibit entailment or not_entailment. answers with 'entailment' or 'not_entailment'. ", | |
"transfer_ori_acc": 93.14079422382672, | |
"transfer_atk_acc": 93.50180505415162 | |
}, | |
{ | |
"dataset": "sst2", | |
"type": "task", | |
"origin_acc": 12.5, | |
"origin_prompt": "After examining the following expression, label its emotion as either 'positive' or 'negative'.", | |
"atk_acc": 0.0, | |
"atk_prompt": "After examining the following action, type its emotion as either 'positive' or 'negative'. ", | |
"transfer_ori_acc": 92.77522935779817, | |
"transfer_atk_acc": 93.69266055045871 | |
}, | |
{ | |
"dataset": "sst2", | |
"type": "role", | |
"origin_acc": 33.37, | |
"origin_prompt": "Taking on the role of an emotion classifier, specify if the provided phrase is 'positive' or 'negative'.", | |
"atk_acc": 0.11, | |
"atk_prompt": "[UNK] on the relationship of an emotion classtoken, choose if the provided phrase is 'positive' or 'negative'. ", | |
"transfer_ori_acc": 95.18348623853211, | |
"transfer_atk_acc": 95.29816513761467 | |
}, | |
{ | |
"dataset": "wnli", | |
"type": "task", | |
"origin_acc": 23.94, | |
"origin_prompt": "Does the relationship between the given sentences represent entailment or not_entailment? Respond with 'entailment' or 'not_entailment'.", | |
"atk_acc": 0.0, | |
"atk_prompt": "Does the relationship between the given sentences represent entailment or not_entailment? q with 'entailment' or 'not_entailment'. ", | |
"transfer_ori_acc": 76.05633802816901, | |
"transfer_atk_acc": 76.05633802816901 | |
}, | |
{ | |
"dataset": "wnli", | |
"type": "role", | |
"origin_acc": 16.9, | |
"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": 0.0, | |
"atk_prompt": "[UNK] your role as an entailment and tool, assess the relationship between the given sentences and classify it as 'entailment' or 'not_entailment'. ", | |
"transfer_ori_acc": 77.46478873239437, | |
"transfer_atk_acc": 77.46478873239437 | |
}, | |
{ | |
"dataset": "mmlu", | |
"type": "task", | |
"origin_acc": 8.51, | |
"origin_prompt": "Evaluate the multiple-choice question about {} and select the most fitting response from 'A', 'B', 'C', or 'D'.", | |
"atk_acc": 3.55, | |
"atk_prompt": "i the multiple-a asked about {} and select the most fitting response from 'A', 'B', 'C', or 'D'. ", | |
"transfer_ori_acc": 53.90070921985816, | |
"transfer_atk_acc": 53.90070921985816 | |
}, | |
{ | |
"dataset": "mmlu", | |
"type": "role", | |
"origin_acc": 9.22, | |
"origin_prompt": "With your understanding of {}, kindly answer the subsequent multiple-choice question by selecting 'A', 'B', 'C', or 'D'.", | |
"atk_acc": 3.37, | |
"atk_prompt": "With your understand of {}, self answer the subsequent multiple-chosen questions by stating 'A', 'B', 'C', or 'D'.", | |
"transfer_ori_acc": 53.72340425531915, | |
"transfer_atk_acc": 53.191489361702125 | |
} | |
] |