Spaces:
Running
Running
[ | |
{ | |
"dataset": "cola", | |
"type": "translation", | |
"origin_acc": 86.9, | |
"origin_prompt": "In the capacity of a grammar assessment system, indicate if the structure of the provided sentence is grammatically correct, responding with 'acceptable' or 'unacceptable'.", | |
"atk_acc": 84.6, | |
"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": 30.5, | |
"transfer_atk_acc": 27.0 | |
}, | |
{ | |
"dataset": "mrpc", | |
"type": "translation", | |
"origin_acc": 88.97, | |
"origin_prompt": "As a sentence similarity evaluator, analyze the provided sentences and indicate if their meanings are 'equivalent' or 'not_equivalent'.", | |
"atk_acc": 84.07, | |
"atk_prompt": "Whether a given pair of sentences is 'equivalent' or 'not_equivalent' depends on the context.", | |
"transfer_ori_acc": 68.13725490196079, | |
"transfer_atk_acc": 66.17647058823529 | |
}, | |
{ | |
"dataset": "qnli", | |
"type": "translation", | |
"origin_acc": 94.5, | |
"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": 83.0, | |
"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": 32.4, | |
"transfer_atk_acc": 35.4 | |
}, | |
{ | |
"dataset": "qqp", | |
"type": "translation", | |
"origin_acc": 90.0, | |
"origin_prompt": "As a tool for determining question equivalence, review the questions and categorize their similarity as either 'equivalent' or 'not_equivalent'.", | |
"atk_acc": 87.7, | |
"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": 31.7, | |
"transfer_atk_acc": 39.2 | |
}, | |
{ | |
"dataset": "rte", | |
"type": "translation", | |
"origin_acc": 93.86, | |
"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": 90.61, | |
"atk_prompt": "Examine the semantic match of a given sentence and categorize it as 'entailment' or 'not_entailment'.", | |
"transfer_ori_acc": 6.4981949458483745, | |
"transfer_atk_acc": 39.71119133574007 | |
}, | |
{ | |
"dataset": "sst2", | |
"type": "translation", | |
"origin_acc": 96.9, | |
"origin_prompt": "Working as a sentiment analyzer, please indicate if the following text is 'positive' or 'negative'.", | |
"atk_acc": 94.38, | |
"atk_prompt": "As an emotion analysis tool, determine whether the emotion in the text is 'positive' or 'negative'.", | |
"transfer_ori_acc": 1.0321100917431194, | |
"transfer_atk_acc": 5.275229357798166 | |
}, | |
{ | |
"dataset": "wnli", | |
"type": "translation", | |
"origin_acc": 77.46, | |
"origin_prompt": "Assess the connection between the following sentences and classify it as 'entailment' or 'not_entailment'.", | |
"atk_acc": 74.65, | |
"atk_prompt": "For the purpose of determining implicative relations, analyze the relations of the following sentences and classify them as 'entailment' or 'not_entailment'.", | |
"transfer_ori_acc": 19.718309859154928, | |
"transfer_atk_acc": 0.0 | |
}, | |
{ | |
"dataset": "mmlu", | |
"type": "translation", | |
"origin_acc": 54.08, | |
"origin_prompt": "For the multiple-choice question related to {}, please choose the most accurate answer from 'A', 'B', 'C', or 'D'.", | |
"atk_acc": 51.95, | |
"atk_prompt": "Choose the correct answer to the multiple-choice question below. Is '{}' an 'A', 'B', 'C', or 'D'.", | |
"transfer_ori_acc": 7.2695035460992905, | |
"transfer_atk_acc": 8.156028368794328 | |
} | |
] |