Spaces:
Runtime error
Runtime error
[ | |
{ | |
"dataset": "cola", | |
"type": "translation", | |
"origin_acc": 86.2, | |
"origin_prompt": "Assess the following sentence and determine if it is grammatically correct. Respond with 'Acceptable' or 'Unacceptable':", | |
"atk_acc": 84.7, | |
"atk_prompt": "As a tool for assessing semantic relevance, categorize the sentence as 'acceptable' or 'unacceptable' according to its meaning and context.", | |
"transfer_ori_acc": 69.0, | |
"transfer_atk_acc": 54.2 | |
}, | |
{ | |
"dataset": "mrpc", | |
"type": "translation", | |
"origin_acc": 88.73, | |
"origin_prompt": "As a sentence similarity evaluator, analyze the provided sentences and indicate if their meanings are 'equivalent' or 'not_equivalent'.", | |
"atk_acc": 81.13, | |
"atk_prompt": "Whether a given pair of sentences is 'equivalent' or 'not_equivalent' depends on the context.", | |
"transfer_ori_acc": 25.98039215686275, | |
"transfer_atk_acc": 21.323529411764707 | |
}, | |
{ | |
"dataset": "qnli", | |
"type": "translation", | |
"origin_acc": 94.6, | |
"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": 78.9, | |
"atk_prompt": "By analyzing the relations between sentences, determine if a given sentence does not necessarily include other sentences and answer with 'entailment' or 'not_entailment'.", | |
"transfer_ori_acc": 38.4, | |
"transfer_atk_acc": 33.800000000000004 | |
}, | |
{ | |
"dataset": "qqp", | |
"type": "translation", | |
"origin_acc": 89.2, | |
"origin_prompt": "While performing question comparison analysis, classify the similarity of the following questions as 'equivalent' for equivalent questions or 'not_equivalent' for different questions.", | |
"atk_acc": 87.4, | |
"atk_prompt": "Classify sentence equivalence as 'equivalent' or 'not_equivalent' by judging whether two sentences have the same meaning to each other.", | |
"transfer_ori_acc": 12.2, | |
"transfer_atk_acc": 12.2 | |
}, | |
{ | |
"dataset": "rte", | |
"type": "translation", | |
"origin_acc": 94.58, | |
"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": 89.89, | |
"atk_prompt": "Examine the paraphrases of a given sentence and classify them 'entailment' or 'not_entailment'.", | |
"transfer_ori_acc": 49.81949458483754, | |
"transfer_atk_acc": 27.075812274368232 | |
}, | |
{ | |
"dataset": "sst2", | |
"type": "translation", | |
"origin_acc": 96.56, | |
"origin_prompt": "In the role of a sentiment analysis tool, respond with 'positive' or 'negative' to classify this statement:", | |
"atk_acc": 93.46, | |
"atk_prompt": "Please analyze the emotion in this sentence and classify it as 'positive' or 'negative'.", | |
"transfer_ori_acc": 32.798165137614674, | |
"transfer_atk_acc": 46.559633027522935 | |
}, | |
{ | |
"dataset": "wnli", | |
"type": "translation", | |
"origin_acc": 80.28, | |
"origin_prompt": "Assess the connection between the following sentences and classify it as 'entailment' or 'not_entailment'.", | |
"atk_acc": 73.24, | |
"atk_prompt": "Given a couple of phrases, label their relationship as 'entailment' if one necessarily implies the other, or as 'not_entailment' if there is no such implication.", | |
"transfer_ori_acc": 38.028169014084504, | |
"transfer_atk_acc": 42.25352112676056 | |
}, | |
{ | |
"dataset": "mmlu", | |
"type": "translation", | |
"origin_acc": 53.19, | |
"origin_prompt": "As an expert in {}, respond to the following multiple-choice question by selecting 'A', 'B', 'C', or 'D'.", | |
"atk_acc": 36.52, | |
"atk_prompt": "Choose the correct answer to the multiple-choice question below. Is '{}' an 'A', 'B', 'C', or 'D'.", | |
"transfer_ori_acc": 23.04964539007092, | |
"transfer_atk_acc": 19.680851063829788 | |
} | |
] |