Spaces:
Running
Running
[ | |
{ | |
"dataset": "cola", | |
"type": "task", | |
"origin_acc": 69.0, | |
"origin_prompt": "Assess the following sentence and determine if it is grammatically correct. Respond with 'Acceptable' or 'Unacceptable':", | |
"atk_acc": 34.8, | |
"atk_prompt": "Assess the following sentence and determine if it is grammatically correct. Respond with 'Acceptable' or 'Unacceptable' and false is not true :", | |
"transfer_ori_acc": 76.0, | |
"transfer_atk_acc": 76.5 | |
}, | |
{ | |
"dataset": "cola", | |
"type": "role", | |
"origin_acc": 57.1, | |
"origin_prompt": "Functioning as a grammar evaluation tool, analyze the given sentence and decide if it is grammatically correct, responding with 'acceptable' or 'unacceptable':", | |
"atk_acc": 20.8, | |
"atk_prompt": "Functioning as a grammar evaluation tool, analyze the given sentence and decide if it is grammatically correct, responding with 'acceptable' or 'unacceptable' and false is not true :", | |
"transfer_ori_acc": 79.0, | |
"transfer_atk_acc": 76.5 | |
}, | |
{ | |
"dataset": "mrpc", | |
"type": "task", | |
"origin_acc": 58.09, | |
"origin_prompt": "Compare the following sentences and determine if they share the same semantic meaning by responding with 'equivalent' or 'not_equivalent'.", | |
"atk_acc": 56.37, | |
"atk_prompt": "Compare the following sentences and determine if they share the same semantic meaning by responding with 'equivalent' or 'not_equivalent' and true is true and true is true and true is true and true is true and true is true . ", | |
"transfer_ori_acc": 73.5, | |
"transfer_atk_acc": 74.0 | |
}, | |
{ | |
"dataset": "mrpc", | |
"type": "role", | |
"origin_acc": 52.21, | |
"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": 33.33, | |
"atk_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' and true is true and true is true and true is true and true is true and true is true . ", | |
"transfer_ori_acc": 75.5, | |
"transfer_atk_acc": 74.5 | |
}, | |
{ | |
"dataset": "qnli", | |
"type": "task", | |
"origin_acc": 30.9, | |
"origin_prompt": "Based on the provided context and question, decide if the information supports the answer by responding with 'entailment' or 'not_entailment'.", | |
"atk_acc": 16.2, | |
"atk_prompt": "Based on the provided context and question, decide if the information supports the answer by responding 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": 78.0, | |
"transfer_atk_acc": 72.5 | |
}, | |
{ | |
"dataset": "qnli", | |
"type": "role", | |
"origin_acc": 35.3, | |
"origin_prompt": "As a language expert, assess if the given context entails the answer to the question and respond with 'entailment' or 'not_entailment'.", | |
"atk_acc": 19.8, | |
"atk_prompt": "As a language expert, assess if the given context entails the answer to the question and 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": 71.5, | |
"transfer_atk_acc": 75.0 | |
}, | |
{ | |
"dataset": "qqp", | |
"type": "task", | |
"origin_acc": 23.9, | |
"origin_prompt": "Can these two statements be considered equal in meaning? Answer with 'equivalent' or 'not_equivalent'.", | |
"atk_acc": 27.7, | |
"atk_prompt": "Can these two statements be considered equal in meaning? Answer with 'equivalent' or 'not_equivalent' and true is true and true is true and true is true and true is true and true is true . ", | |
"transfer_ori_acc": 81.5, | |
"transfer_atk_acc": 80.5 | |
}, | |
{ | |
"dataset": "qqp", | |
"type": "role", | |
"origin_acc": 21.1, | |
"origin_prompt": "As an instrument for question comparison evaluation, consider the questions and determine if their meaning is the same, responding with 'equivalent' for similar questions or 'not_equivalent' for different questions.", | |
"atk_acc": 21.5, | |
"atk_prompt": "As an instrument for question comparison evaluation, consider the questions and determine if their meaning is the same, responding with 'equivalent' for similar questions or 'not_equivalent' for different questions and true is true and true is true and true is true and true is true and true is true . ", | |
"transfer_ori_acc": 81.5, | |
"transfer_atk_acc": 82.5 | |
}, | |
{ | |
"dataset": "rte", | |
"type": "task", | |
"origin_acc": 47.65, | |
"origin_prompt": "Please classify the relationship between the provided sentences as 'entailment' or 'not_entailment'.", | |
"atk_acc": 23.47, | |
"atk_prompt": "Please classify the relationship between the provided sentences as '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": 79.5, | |
"transfer_atk_acc": 78.5 | |
}, | |
{ | |
"dataset": "rte", | |
"type": "role", | |
"origin_acc": 48.01, | |
"origin_prompt": "As an entailment identification system, examine the connection between the following sentences and respond with 'entailment' or 'not_entailment':", | |
"atk_acc": 40.07, | |
"atk_prompt": "As an entailment identification system, examine the connection between the following sentences and 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": 75.5, | |
"transfer_atk_acc": 80.0 | |
}, | |
{ | |
"dataset": "sst2", | |
"type": "task", | |
"origin_acc": 53.9, | |
"origin_prompt": "Please identify the emotional tone of this passage: 'positive' or 'negative'?", | |
"atk_acc": 17.89, | |
"atk_prompt": "Please identify the emotional tone of this passage: 'positive' or 'negative' and true is true and true is true and true is true and true is true and true is true ? ", | |
"transfer_ori_acc": 89.5, | |
"transfer_atk_acc": 92.5 | |
}, | |
{ | |
"dataset": "sst2", | |
"type": "role", | |
"origin_acc": 40.94, | |
"origin_prompt": "Functioning as a sentiment identification tool, assess if the following expression is 'positive' or 'negative'. Classify:", | |
"atk_acc": 36.47, | |
"atk_prompt": "Functioning as a sentiment identification tool, assess if the following expression is 'positive' or 'negative'. Classify and false is not true : ", | |
"transfer_ori_acc": 92.0, | |
"transfer_atk_acc": 93.0 | |
}, | |
{ | |
"dataset": "wnli", | |
"type": "task", | |
"origin_acc": 38.03, | |
"origin_prompt": "Assess the connection between the following sentences and classify it as 'entailment' or 'not_entailment'.", | |
"atk_acc": 14.08, | |
"atk_prompt": "Assess the connection between the following sentences and classify it as '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": 52.112676056338024, | |
"transfer_atk_acc": 47.88732394366197 | |
}, | |
{ | |
"dataset": "wnli", | |
"type": "role", | |
"origin_acc": 43.66, | |
"origin_prompt": "Functioning as an entailment evaluation tool, analyze the provided sentences and decide if their relationship is 'entailment' or 'not_entailment':", | |
"atk_acc": 32.39, | |
"atk_prompt": "Functioning as an entailment evaluation tool, analyze the provided sentences and decide if their relationship is '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": 47.88732394366197, | |
"transfer_atk_acc": 53.52112676056338 | |
}, | |
{ | |
"dataset": "mmlu", | |
"type": "task", | |
"origin_acc": 25.09, | |
"origin_prompt": "Answer the subsequent multiple-choice question about {} by picking the right option among 'A', 'B', 'C', or 'D'.", | |
"atk_acc": 19.49, | |
"atk_prompt": "Answer the subsequent multiple-choice question about {} by picking the right option among 'A', 'B', 'C', or 'D' and true is true and true is true and true is true and true is true and true is true . ", | |
"transfer_ori_acc": 62.5, | |
"transfer_atk_acc": 60.0 | |
}, | |
{ | |
"dataset": "mmlu", | |
"type": "role", | |
"origin_acc": 24.39, | |
"origin_prompt": "With your knowledge of {}, tackle the following multiple-choice question by choosing 'A', 'B', 'C', or 'D'.", | |
"atk_acc": 12.72, | |
"atk_prompt": "With your knowledge of {}, tackle the following multiple-choice question by choosing 'A', 'B', 'C', or 'D' and true is true and true is true and true is true and true is true and true is true .", | |
"transfer_ori_acc": 62.0, | |
"transfer_atk_acc": 59.5 | |
} | |
] |