Spaces:
Runtime error
Runtime error
[ | |
{ | |
"dataset": "cola", | |
"type": "translation", | |
"origin_acc": 79.5, | |
"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": 25.0, | |
"atk_prompt": "Classify the grammar of a given sentence into two categories, 'acceptable' or 'unacceptable', and judge its accuracy.", | |
"transfer_ori_acc": 57.099999999999994, | |
"transfer_atk_acc": 31.5 | |
}, | |
{ | |
"dataset": "mrpc", | |
"type": "translation", | |
"origin_acc": 76.5, | |
"origin_prompt": "Can the given sentences be considered semantically identical? Please reply with 'equivalent' or 'not_equivalent'.", | |
"atk_acc": 7.0, | |
"atk_prompt": "As an expert in semantic comparison, assess the similarity between the following two sentences and determine whether they are 'equivalent' or 'not_equivalent'.", | |
"transfer_ori_acc": 53.431372549019606, | |
"transfer_atk_acc": 26.225490196078432 | |
}, | |
{ | |
"dataset": "qnli", | |
"type": "translation", | |
"origin_acc": 79.5, | |
"origin_prompt": "Assess if the answer to the question can be logically concluded from the provided context by choosing 'entailment' or 'not_entailment'.", | |
"atk_acc": 56.5, | |
"atk_prompt": "Check the text link to the question and answer 'entailment' or 'not_entailment', depending on your language skills.", | |
"transfer_ori_acc": 19.7, | |
"transfer_atk_acc": 5.2 | |
}, | |
{ | |
"dataset": "qqp", | |
"type": "translation", | |
"origin_acc": 84.0, | |
"origin_prompt": "Determine if the given pair of statements can be considered the same by responding with 'equivalent' or 'not_equivalent'.", | |
"atk_acc": 3.0, | |
"atk_prompt": "As a tool for determining the equivalence of problems, the problems are examined and their similarity is classified as 'equivalent' or 'not_equivalent'.", | |
"transfer_ori_acc": 13.5, | |
"transfer_atk_acc": 2.3 | |
}, | |
{ | |
"dataset": "rte", | |
"type": "translation", | |
"origin_acc": 84.0, | |
"origin_prompt": "Determine if the given pair of sentences displays entailment or not_entailment. Respond with 'entailment' or 'not_entailment'.", | |
"atk_acc": 39.0, | |
"atk_prompt": "Determine whether the given sentences have a cause-effect relationship as an engagement analysis tool and categorize them as 'entailment' or 'not_entailment'.", | |
"transfer_ori_acc": 41.15523465703971, | |
"transfer_atk_acc": 22.382671480144403 | |
}, | |
{ | |
"dataset": "sst2", | |
"type": "translation", | |
"origin_acc": 96.0, | |
"origin_prompt": "Read the provided excerpt and choose between 'positive' and 'negative' to describe its sentiment:", | |
"atk_acc": 29.5, | |
"atk_prompt": "In the context of textual analysis, what classification is this phrase between 'positive' and 'negative'?", | |
"transfer_ori_acc": 27.981651376146786, | |
"transfer_atk_acc": 44.8394495412844 | |
}, | |
{ | |
"dataset": "wnli", | |
"type": "translation", | |
"origin_acc": 67.61, | |
"origin_prompt": "Examine the pair of sentences and determine if they exhibit entailment or not_entailment. Answer with either 'entailment' or 'not_entailment'.", | |
"atk_acc": 26.76, | |
"atk_prompt": "Using implication analysis, determine whether the given sentences have a cause-effect relationship and categorize them as 'entailment' or 'not_entailment'.", | |
"transfer_ori_acc": 33.80281690140845, | |
"transfer_atk_acc": 36.61971830985916 | |
}, | |
{ | |
"dataset": "mmlu", | |
"type": "translation", | |
"origin_acc": 64.0, | |
"origin_prompt": "In relation to the multiple-choice question on {}, please provide the accurate answer by choosing 'A', 'B', 'C', or 'D'.", | |
"atk_acc": 49.5, | |
"atk_prompt": "Choose the correct answer to the multiple-choice question below. Is '{}' an 'A', 'B', 'C', or 'D'.", | |
"transfer_ori_acc": 19.326241134751772, | |
"transfer_atk_acc": 19.680851063829788 | |
} | |
] |