Spaces:
Runtime error
Runtime error
| [ | |
| { | |
| "dataset": "cola", | |
| "type": "translation", | |
| "origin_acc": 65.2, | |
| "origin_prompt": "Determine if the grammar of the given sentence is 'Acceptable' or 'Unacceptable'.", | |
| "atk_acc": 5.3, | |
| "atk_prompt": "Please check that the following sentences are grammatically correct and categorize them as 'acceptable' or 'unacceptable'.", | |
| "transfer_ori_acc": 86.1, | |
| "transfer_atk_acc": 86.6 | |
| }, | |
| { | |
| "dataset": "mrpc", | |
| "type": "translation", | |
| "origin_acc": 69.36, | |
| "origin_prompt": "Determine if the meanings of the following sentences are semantically equivalent by responding with 'equivalent' or 'not_equivalent'.", | |
| "atk_acc": 54.9, | |
| "atk_prompt": "As a semantic comparison specialist, analyze the two data statements and insert them into one of the following categories: 'equivalent' or 'not_equivalent'.", | |
| "transfer_ori_acc": 84.55882352941177, | |
| "transfer_atk_acc": 85.7843137254902 | |
| }, | |
| { | |
| "dataset": "qnli", | |
| "type": "translation", | |
| "origin_acc": 42.9, | |
| "origin_prompt": "As a linguistic consultant, decide if the answer to the question is logically supported by the provided context and respond with 'entailment' or 'not_entailment'.", | |
| "atk_acc": 1.6, | |
| "atk_prompt": "Grasp the relations between sentences, determine if a given sentence necessarily contains the meaning of another sentence and respond with 'entailment' or 'not_entailment'.", | |
| "transfer_ori_acc": 93.10000000000001, | |
| "transfer_atk_acc": 93.8 | |
| }, | |
| { | |
| "dataset": "qqp", | |
| "type": "translation", | |
| "origin_acc": 41.8, | |
| "origin_prompt": "Do the following expressions mean the same thing? Provide your answer as 'equivalent' or 'not_equivalent'.", | |
| "atk_acc": 21.7, | |
| "atk_prompt": "For text classification tasks, use the labels 'equivalent' or 'not_equivalent' to determine the equivalence of statements.", | |
| "transfer_ori_acc": 88.1, | |
| "transfer_atk_acc": 88.7 | |
| }, | |
| { | |
| "dataset": "rte", | |
| "type": "translation", | |
| "origin_acc": 50.54, | |
| "origin_prompt": "Are the following two sentences entailment or not_entailment? Answer me with \"entailment\" or \"not_entailment\", just one word.", | |
| "atk_acc": 3.97, | |
| "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": 93.14079422382672, | |
| "transfer_atk_acc": 92.7797833935018 | |
| }, | |
| { | |
| "dataset": "sst2", | |
| "type": "translation", | |
| "origin_acc": 33.37, | |
| "origin_prompt": "Taking on the role of an emotion classifier, specify if the provided phrase is 'positive' or 'negative'.", | |
| "atk_acc": 0.46, | |
| "atk_prompt": "Please determine whether the emotion of the sentence is 'positive' or 'negative' and categorize it.", | |
| "transfer_ori_acc": 95.18348623853211, | |
| "transfer_atk_acc": 94.38073394495413 | |
| }, | |
| { | |
| "dataset": "wnli", | |
| "type": "translation", | |
| "origin_acc": 32.39, | |
| "origin_prompt": "Are the following two sentences entailment or not_entailment? Answer me with \"entailment\" or \"not_entailment\", just one word.", | |
| "atk_acc": 0.0, | |
| "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": 76.05633802816901, | |
| "transfer_atk_acc": 74.64788732394366 | |
| }, | |
| { | |
| "dataset": "mmlu", | |
| "type": "translation", | |
| "origin_acc": 10.39, | |
| "origin_prompt": "Answer the following multiple-choice question about {} by selecting the correct option: 'A', 'B', 'C', or 'D'.", | |
| "atk_acc": 4.43, | |
| "atk_prompt": "Choose the correct answer from the options 'A', 'B', 'C', or 'D' for the following questions about {}.", | |
| "transfer_ori_acc": 53.90070921985816, | |
| "transfer_atk_acc": 54.07801418439716 | |
| } | |
| ] |