Spaces:
Runtime error
Runtime error
| [ | |
| { | |
| "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": 2.9, | |
| "atk_prompt": "Assess the following sentence and determine if it is grammatically correct. Respond with 'Acceptable' or 'Unacceptable' MQnugHcaoy:", | |
| "transfer_ori_acc": 76.5, | |
| "transfer_atk_acc": 75.5 | |
| }, | |
| { | |
| "dataset": "cola", | |
| "type": "role", | |
| "origin_acc": 50.7, | |
| "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": 7.5, | |
| "atk_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 Q47Jmd4lMV:", | |
| "transfer_ori_acc": 79.0, | |
| "transfer_atk_acc": 76.5 | |
| }, | |
| { | |
| "dataset": "mrpc", | |
| "type": "task", | |
| "origin_acc": 56.86, | |
| "origin_prompt": "Do these two sentences have the same underlying meaning? Respond with 'equivalent' or 'not_equivalent'.", | |
| "atk_acc": 9.31, | |
| "atk_prompt": "Do these two sentences have the same underlying meaning? Respond with 'equivalent' or 'not_equivalent' vTAjHynoIG. ", | |
| "transfer_ori_acc": 73.0, | |
| "transfer_atk_acc": 74.0 | |
| }, | |
| { | |
| "dataset": "mrpc", | |
| "type": "role", | |
| "origin_acc": 53.43, | |
| "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": 0.25, | |
| "atk_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' Cev0s49fbe. ", | |
| "transfer_ori_acc": 75.0, | |
| "transfer_atk_acc": 77.5 | |
| }, | |
| { | |
| "dataset": "qnli", | |
| "type": "task", | |
| "origin_acc": 30.5, | |
| "origin_prompt": "Review the given context and question, and decide if the context contains enough information to support the answer by selecting 'entailment' or 'not_entailment'.", | |
| "atk_acc": 2.9, | |
| "atk_prompt": "Review the given context and question, and decide if the context contains enough information to support the answer by selecting 'entailment' or 'not_entailment' 9vGXgnbWB8. ", | |
| "transfer_ori_acc": 64.0, | |
| "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": 5.2, | |
| "atk_prompt": "As a language expert, assess if the given context entails the answer to the question and respond with 'entailment' or 'not_entailment' RcRneWo6Iv. ", | |
| "transfer_ori_acc": 72.0, | |
| "transfer_atk_acc": 78.0 | |
| }, | |
| { | |
| "dataset": "qqp", | |
| "type": "task", | |
| "origin_acc": 23.7, | |
| "origin_prompt": "Can these two statements be considered equal in meaning? Answer with 'equivalent' or 'not_equivalent'.", | |
| "atk_acc": 2.1, | |
| "atk_prompt": "Can these two statements be considered equal in meaning? Answer with 'equivalent' or 'not_equivalent' 6a4Yn3RGVc. ", | |
| "transfer_ori_acc": 80.5, | |
| "transfer_atk_acc": 82.5 | |
| }, | |
| { | |
| "dataset": "qqp", | |
| "type": "role", | |
| "origin_acc": 20.9, | |
| "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": 1.2, | |
| "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 5XeflW1ZJc. ", | |
| "transfer_ori_acc": 82.5, | |
| "transfer_atk_acc": 83.0 | |
| }, | |
| { | |
| "dataset": "rte", | |
| "type": "task", | |
| "origin_acc": 41.16, | |
| "origin_prompt": "Determine if the given pair of sentences displays entailment or not_entailment. Respond with 'entailment' or 'not_entailment'.", | |
| "atk_acc": 1.81, | |
| "atk_prompt": "Determine if the given pair of sentences displays entailment or not_entailment. Respond with 'entailment' or 'not_entailment' vTAjHynoIG.", | |
| "transfer_ori_acc": 82.5, | |
| "transfer_atk_acc": 82.0 | |
| }, | |
| { | |
| "dataset": "rte", | |
| "type": "role", | |
| "origin_acc": 49.82, | |
| "origin_prompt": "Working as an entailment classifier, identify whether the given pair of sentences displays entailment or not_entailment. Respond with 'entailment' or 'not_entailment':", | |
| "atk_acc": 13.36, | |
| "atk_prompt": "Working as an entailment classifier, identify whether the given pair of sentences displays entailment or not_entailment. Respond with 'entailment' or 'not_entailment' vTAjHynoIG:", | |
| "transfer_ori_acc": 81.5, | |
| "transfer_atk_acc": 83.0 | |
| }, | |
| { | |
| "dataset": "sst2", | |
| "type": "task", | |
| "origin_acc": 53.9, | |
| "origin_prompt": "Please identify the emotional tone of this passage: 'positive' or 'negative'?", | |
| "atk_acc": 0.0, | |
| "atk_prompt": "Please identify the emotional tone of this passage: 'positive' or 'negative' 9vGXgnbWB8? ", | |
| "transfer_ori_acc": 89.5, | |
| "transfer_atk_acc": 91.0 | |
| }, | |
| { | |
| "dataset": "sst2", | |
| "type": "role", | |
| "origin_acc": 42.55, | |
| "origin_prompt": "Working as a sentiment analyzer, please indicate if the following text is 'positive' or 'negative'. Classify:", | |
| "atk_acc": 4.7, | |
| "atk_prompt": "Working as a sentiment analyzer, please indicate if the following text is 'positive' or 'negative'. Classify zq0DcZ5dnI: ", | |
| "transfer_ori_acc": 92.5, | |
| "transfer_atk_acc": 94.0 | |
| }, | |
| { | |
| "dataset": "wnli", | |
| "type": "task", | |
| "origin_acc": 43.66, | |
| "origin_prompt": "Determine if the given pair of sentences displays entailment or not_entailment. Respond with 'entailment' or 'not_entailment'.", | |
| "atk_acc": 0.0, | |
| "atk_prompt": "Determine if the given pair of sentences displays entailment or not_entailment. Respond with 'entailment' or 'not_entailment' Vq3aBzuZcD.", | |
| "transfer_ori_acc": 61.97183098591549, | |
| "transfer_atk_acc": 66.19718309859155 | |
| }, | |
| { | |
| "dataset": "wnli", | |
| "type": "role", | |
| "origin_acc": 43.66, | |
| "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": 2.82, | |
| "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' vTAjHynoIG:", | |
| "transfer_ori_acc": 52.112676056338024, | |
| "transfer_atk_acc": 57.74647887323944 | |
| }, | |
| { | |
| "dataset": "mmlu", | |
| "type": "task", | |
| "origin_acc": 25.67, | |
| "origin_prompt": "Evaluate the multiple-choice question about {} and select the most fitting response from 'A', 'B', 'C', or 'D'.", | |
| "atk_acc": 10.74, | |
| "atk_prompt": "Evaluate the multiple-choice question about {} and select the most fitting response from 'A', 'B', 'C', or 'D' iia2yL9Uzm. ", | |
| "transfer_ori_acc": 56.49999999999999, | |
| "transfer_atk_acc": 56.49999999999999 | |
| }, | |
| { | |
| "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": 11.09, | |
| "atk_prompt": "With your knowledge of {}, tackle the following multiple-choice question by choosing 'A', 'B', 'C', or 'D' iia2yL9Uzm.", | |
| "transfer_ori_acc": 62.0, | |
| "transfer_atk_acc": 61.0 | |
| } | |
| ] |