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": 78.0, | |
"transfer_atk_acc": 75.7 | |
}, | |
{ | |
"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": 80.63725490196079, | |
"transfer_atk_acc": 83.08823529411765 | |
}, | |
{ | |
"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": 89.4, | |
"transfer_atk_acc": 85.6 | |
}, | |
{ | |
"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": 86.6, | |
"transfer_atk_acc": 86.1 | |
}, | |
{ | |
"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": 83.03249097472924, | |
"transfer_atk_acc": 81.58844765342961 | |
}, | |
{ | |
"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": 95.41284403669725, | |
"transfer_atk_acc": 93.80733944954129 | |
}, | |
{ | |
"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": 61.97183098591549, | |
"transfer_atk_acc": 64.7887323943662 | |
}, | |
{ | |
"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": 44.680851063829785, | |
"transfer_atk_acc": 43.262411347517734 | |
}, | |
{ | |
"dataset": "squad_v2", | |
"type": "translation", | |
"origin_acc": 90.05, | |
"origin_prompt": "Please derive the most fitting answer from the context. If there isn't an answer in the context, respond with 'unanswerable'.", | |
"atk_acc": 84.45, | |
"atk_prompt": "Please give a solution to what kind of problem in the following sentence. If there is no solution, respond with 'unanswerable'.", | |
"transfer_ori_acc": 87.64992770387508, | |
"transfer_atk_acc": 85.51584249084247 | |
}, | |
{ | |
"dataset": "iwslt", | |
"type": "translation", | |
"origin_acc": 0.18, | |
"origin_prompt": "Accurately translate the sentence from {} to {}, ensuring the meaning remains intact:", | |
"atk_acc": 0.16, | |
"atk_prompt": "Please translate the given sentence into {} to {}.", | |
"transfer_ori_acc": 0.13434360012327884, | |
"transfer_atk_acc": 0.1321435432036806 | |
}, | |
{ | |
"dataset": "un_multi", | |
"type": "translation", | |
"origin_acc": 0.32, | |
"origin_prompt": "Please perform a translation of the given sentence, converting it from {} to {}:", | |
"atk_acc": 0.31, | |
"atk_prompt": "Please translate the given sentence, converting it from {} to {}.", | |
"transfer_ori_acc": 0.2683567351751297, | |
"transfer_atk_acc": 0.268967122899458 | |
}, | |
{ | |
"dataset": "math", | |
"type": "translation", | |
"origin_acc": 15.62, | |
"origin_prompt": "Act as a math expert and compute the result of the following mathematical task about {}:", | |
"atk_acc": 14.37, | |
"atk_prompt": "According to {}, determine the next value.", | |
"transfer_ori_acc": 3.125, | |
"transfer_atk_acc": 14.374999999999998 | |
} | |
] |