Spaces:
Runtime error
Runtime error
[ | |
{ | |
"dataset": "cola", | |
"type": "task", | |
"origin_acc": 86.4, | |
"origin_prompt": "Review the sentence below and identify whether its grammar is 'Acceptable' or 'Unacceptable'.", | |
"atk_acc": 85.4, | |
"atk_prompt": "Review the sentence below and identify whether its grammar is 'Acceptable' or 'Unacceptable' and true is true and true is true and true is true and true is true and true is true . ", | |
"transfer_ori_acc": 26.0, | |
"transfer_atk_acc": 6.6000000000000005 | |
}, | |
{ | |
"dataset": "cola", | |
"type": "role", | |
"origin_acc": 86.6, | |
"origin_prompt": "While performing grammar analysis, classify the grammar of the following sentence as 'acceptable' for correct grammar or 'unacceptable' for incorrect grammar.", | |
"atk_acc": 86.1, | |
"atk_prompt": "While performing grammar analysis, classify the grammar of the following sentence as 'acceptable' for correct grammar or 'unacceptable' for incorrect grammar and true is true and true is true and true is true and true is true and true is true . ", | |
"transfer_ori_acc": 49.9, | |
"transfer_atk_acc": 30.9 | |
}, | |
{ | |
"dataset": "mrpc", | |
"type": "task", | |
"origin_acc": 86.76, | |
"origin_prompt": "Compare the following sentences and determine if they share the same semantic meaning by responding with 'equivalent' or 'not_equivalent'.", | |
"atk_acc": 85.78, | |
"atk_prompt": "Compare the following sentences and determine if they share the same semantic meaning by responding with 'equivalent' or 'not_equivalent' and false is not true . ", | |
"transfer_ori_acc": 62.254901960784316, | |
"transfer_atk_acc": 66.42156862745098 | |
}, | |
{ | |
"dataset": "mrpc", | |
"type": "role", | |
"origin_acc": 87.5, | |
"origin_prompt": "As a textual similarity evaluator, analyze the following pair of sentences and determine if they are semantically 'equivalent' or 'not_equivalent'.", | |
"atk_acc": 87.01, | |
"atk_prompt": "As a textual similarity evaluator, analyze the following pair of sentences and determine if they are semantically 'equivalent' or 'not_equivalent' and false is not true . ", | |
"transfer_ori_acc": 59.31372549019608, | |
"transfer_atk_acc": 63.725490196078425 | |
}, | |
{ | |
"dataset": "qnli", | |
"type": "task", | |
"origin_acc": 94.0, | |
"origin_prompt": "Analyze the context and question, and indicate if the context entails the answer by choosing 'entailment' or 'not_entailment'.", | |
"atk_acc": 93.9, | |
"atk_prompt": "Analyze the context and question, and indicate if the context entails the answer by choosing 'entailment' or 'not_entailment' and true is true and true is true and true is true and true is true and true is true . ", | |
"transfer_ori_acc": 35.0, | |
"transfer_atk_acc": 12.1 | |
}, | |
{ | |
"dataset": "qnli", | |
"type": "role", | |
"origin_acc": 93.9, | |
"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": 94.0, | |
"atk_prompt": "As a semantic researcher, evaluate whether the provided context supports the answer to the question and choose 'entailment' or 'not_entailment' and true is true . ", | |
"transfer_ori_acc": 41.6, | |
"transfer_atk_acc": 40.9 | |
}, | |
{ | |
"dataset": "qqp", | |
"type": "task", | |
"origin_acc": 88.5, | |
"origin_prompt": "Are the following two questions equivalent or not? Answer me with \"equivalent\" or \"not_equivalent\".", | |
"atk_acc": 88.0, | |
"atk_prompt": "Are the following two questions equivalent or not? Answer me with \"equivalent\" or \"not_equivalent and true is true \". ", | |
"transfer_ori_acc": 34.8, | |
"transfer_atk_acc": 47.8 | |
}, | |
{ | |
"dataset": "qqp", | |
"type": "role", | |
"origin_acc": 89.1, | |
"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": 88.9, | |
"atk_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' and false is not true . ", | |
"transfer_ori_acc": 32.9, | |
"transfer_atk_acc": 41.4 | |
}, | |
{ | |
"dataset": "rte", | |
"type": "task", | |
"origin_acc": 93.5, | |
"origin_prompt": "Does the relationship between the given sentences represent entailment or not_entailment? Respond with 'entailment' or 'not_entailment'.", | |
"atk_acc": 92.78, | |
"atk_prompt": "Does the relationship between the given sentences represent entailment or not_entailment? Respond with 'entailment' or 'not_entailment' and true is true and true is true and true is true and true is true and true is true . ", | |
"transfer_ori_acc": 46.20938628158845, | |
"transfer_atk_acc": 35.37906137184115 | |
}, | |
{ | |
"dataset": "rte", | |
"type": "role", | |
"origin_acc": 93.5, | |
"origin_prompt": "As a tool for determining entailment relationships, review the two statements and categorize their connection as either 'entailment' or 'not_entailment'.", | |
"atk_acc": 92.06, | |
"atk_prompt": "As a tool for determining entailment relationships, review the two statements and categorize their connection as either 'entailment' or 'not_entailment' and true is true and true is true and true is true and true is true and true is true . ", | |
"transfer_ori_acc": 28.158844765342963, | |
"transfer_atk_acc": 5.776173285198556 | |
}, | |
{ | |
"dataset": "sst2", | |
"type": "task", | |
"origin_acc": 96.79, | |
"origin_prompt": "Determine the overall sentiment of this sentence, categorizing it as 'positive' or 'negative'.", | |
"atk_acc": 96.67, | |
"atk_prompt": "Determine the overall sentiment of this sentence, categorizing it as 'positive' or 'negative' and false is not true . ", | |
"transfer_ori_acc": 0.573394495412844, | |
"transfer_atk_acc": 0.11467889908256881 | |
}, | |
{ | |
"dataset": "sst2", | |
"type": "role", | |
"origin_acc": 96.56, | |
"origin_prompt": "As a sentiment classifier, determine whether the following text is 'positive' or 'negative'.", | |
"atk_acc": 96.33, | |
"atk_prompt": "As a sentiment classifier, determine whether the following text is 'positive' or 'negative' and false is not true . ", | |
"transfer_ori_acc": 15.36697247706422, | |
"transfer_atk_acc": 8.486238532110093 | |
}, | |
{ | |
"dataset": "wnli", | |
"type": "task", | |
"origin_acc": 77.46, | |
"origin_prompt": "Please classify the relationship between the provided sentences as 'entailment' or 'not_entailment'.", | |
"atk_acc": 74.65, | |
"atk_prompt": "Please classify the relationship between the provided sentences as 'entailment' or 'not_entailment' and false is not true . ", | |
"transfer_ori_acc": 21.12676056338028, | |
"transfer_atk_acc": 9.859154929577464 | |
}, | |
{ | |
"dataset": "wnli", | |
"type": "role", | |
"origin_acc": 76.06, | |
"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": 74.65, | |
"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' and false is not true . ", | |
"transfer_ori_acc": 23.943661971830984, | |
"transfer_atk_acc": 32.3943661971831 | |
}, | |
{ | |
"dataset": "mmlu", | |
"type": "task", | |
"origin_acc": 53.9, | |
"origin_prompt": "Below are multiple-choice question concerning {}. Indicate your response with 'A', 'B', 'C', or 'D'.", | |
"atk_acc": 51.77, | |
"atk_prompt": "Below are multiple-choice question concerning {}. Indicate your response with 'A', 'B', 'C', or 'D' and false is not true . ", | |
"transfer_ori_acc": 6.382978723404255, | |
"transfer_atk_acc": 9.042553191489363 | |
}, | |
{ | |
"dataset": "mmlu", | |
"type": "role", | |
"origin_acc": 54.08, | |
"origin_prompt": "Considering your familiarity with {}, attend to the following multiple-choice question by picking 'A', 'B', 'C', or 'D'.", | |
"atk_acc": 51.42, | |
"atk_prompt": "Considering your familiarity with {}, attend to the following multiple-choice question by picking 'A', 'B', 'C', or 'D' and false is not true .", | |
"transfer_ori_acc": 8.156028368794328, | |
"transfer_atk_acc": 16.666666666666664 | |
} | |
] |