Spaces:
Running
Running
[ | |
{ | |
"dataset": "cola", | |
"type": "translation", | |
"origin_acc": 78.1, | |
"origin_prompt": "Assess the following sentence and determine if it is grammatically correct. Respond with 'Acceptable' or 'Unacceptable'.", | |
"atk_acc": 74.0, | |
"atk_prompt": "When evaluating the grammar of the sentence, classify it as 'acceptable' or 'unacceptable' according to the rules of the French language.", | |
"transfer_ori_acc": 86.1, | |
"transfer_atk_acc": 86.4 | |
}, | |
{ | |
"dataset": "mrpc", | |
"type": "translation", | |
"origin_acc": 83.09, | |
"origin_prompt": "Evaluate whether the two provided sentences convey the same meaning by answering 'equivalent' or 'not_equivalent'.", | |
"atk_acc": 79.66, | |
"atk_prompt": "Using the semantic comparison method, determine whether the following two statements are 'equivalent' or 'not_equivalent'.", | |
"transfer_ori_acc": 85.7843137254902, | |
"transfer_atk_acc": 85.29411764705883 | |
}, | |
{ | |
"dataset": "qnli", | |
"type": "translation", | |
"origin_acc": 89.3, | |
"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": 54.8, | |
"atk_prompt": "Answer with 'entailment' or 'not_entailment', inferring from the given context.", | |
"transfer_ori_acc": 94.5, | |
"transfer_atk_acc": 93.0 | |
}, | |
{ | |
"dataset": "qqp", | |
"type": "translation", | |
"origin_acc": 88.1, | |
"origin_prompt": "Are the following two questions equivalent or not? Answer me with \"equivalent\" or \"not_equivalent\".", | |
"atk_acc": 77.9, | |
"atk_prompt": "As a tool for determining equivalence, check sentences and categorize them into 'equivalent' or 'not_equivalent' categories.", | |
"transfer_ori_acc": 88.5, | |
"transfer_atk_acc": 89.0 | |
}, | |
{ | |
"dataset": "rte", | |
"type": "translation", | |
"origin_acc": 85.2, | |
"origin_prompt": "Are the following two sentences entailment or not_entailment? Answer me with \"entailment\" or \"not_entailment\", just one word.", | |
"atk_acc": 79.78, | |
"atk_prompt": "Rate the similarity of a given sentence and categorize it as 'entailment' or 'not_entailment'.", | |
"transfer_ori_acc": 93.14079422382672, | |
"transfer_atk_acc": 91.69675090252709 | |
}, | |
{ | |
"dataset": "sst2", | |
"type": "translation", | |
"origin_acc": 95.53, | |
"origin_prompt": "In the role of a sentiment analysis tool, respond with 'positive' or 'negative' to classify this statement.", | |
"atk_acc": 93.23, | |
"atk_prompt": "As an emotion analysis tool, determine whether the emotion in the text is 'positive' or 'negative'.", | |
"transfer_ori_acc": 96.67431192660551, | |
"transfer_atk_acc": 94.4954128440367 | |
}, | |
{ | |
"dataset": "wnli", | |
"type": "translation", | |
"origin_acc": 66.2, | |
"origin_prompt": "Are the following two sentences entailment or not_entailment? Answer me with \"entailment\" or \"not_entailment\", just one word.", | |
"atk_acc": 49.3, | |
"atk_prompt": "Examine the paraphrases of a given sentence and classify them 'entailment' or 'not_entailment'.", | |
"transfer_ori_acc": 76.05633802816901, | |
"transfer_atk_acc": 80.28169014084507 | |
}, | |
{ | |
"dataset": "mmlu", | |
"type": "translation", | |
"origin_acc": 46.99, | |
"origin_prompt": "As an expert in {}, respond to the following multiple-choice question by selecting 'A', 'B', 'C', or 'D'.", | |
"atk_acc": 43.97, | |
"atk_prompt": "Choose the correct answer for '{}' from 'A', 'B', 'C', or 'D' in the multiple choice problem involving,", | |
"transfer_ori_acc": 53.72340425531915, | |
"transfer_atk_acc": 53.36879432624113 | |
}, | |
{ | |
"dataset": "squad_v2", | |
"type": "translation", | |
"origin_acc": 87.91, | |
"origin_prompt": "From the context, provide the most precise answer. If the answer is not in the context, respond with 'unanswerable'.", | |
"atk_acc": 86.22, | |
"atk_prompt": "Briefly describes the situation and provides the corresponding response. If the answer cannot be found, answer with 'unanswerable'.", | |
"transfer_ori_acc": 89.38229949874687, | |
"transfer_atk_acc": 90.88229949874687 | |
}, | |
{ | |
"dataset": "iwslt", | |
"type": "translation", | |
"origin_acc": 0.22, | |
"origin_prompt": "Convert the following sentence from its original {} language to the target language {}.", | |
"atk_acc": 0.2, | |
"atk_prompt": "Please translate the sentences below into {}, then {}.", | |
"transfer_ori_acc": 0.23981220411098694, | |
"transfer_atk_acc": 0.23367230863817542 | |
}, | |
{ | |
"dataset": "un_multi", | |
"type": "translation", | |
"origin_acc": 0.31, | |
"origin_prompt": "Translate the provided sentence from {} to {} while maintaining the original meaning and context.", | |
"atk_acc": 0.3, | |
"atk_prompt": "Please translate the given sentence into {} to {}.", | |
"transfer_ori_acc": 0.35929731147922295, | |
"transfer_atk_acc": 0.35719628133790055 | |
}, | |
{ | |
"dataset": "math", | |
"type": "translation", | |
"origin_acc": 18.12, | |
"origin_prompt": "Embodying a mathematics advisor, find the answer to the following math problem with {}.", | |
"atk_acc": 15.62, | |
"atk_prompt": "According to {}, set the following value.", | |
"transfer_ori_acc": 15.0, | |
"transfer_atk_acc": 16.25 | |
} | |
] |