Spaces:
Runtime error
Runtime error
| [ | |
| { | |
| "dataset": "cola", | |
| "type": "translation", | |
| "origin_acc": 69.0, | |
| "origin_prompt": "Assess the following sentence and determine if it is grammatically correct. Respond with 'Acceptable' or 'Unacceptable':", | |
| "atk_acc": 5.8, | |
| "atk_prompt": "As a tool for analyzing grammatical correctness, it categorizes the grammatical rules of the sentence as 'acceptable' or 'unacceptable'.", | |
| "transfer_ori_acc": 86.2, | |
| "transfer_atk_acc": 85.1 | |
| }, | |
| { | |
| "dataset": "mrpc", | |
| "type": "translation", | |
| "origin_acc": 67.16, | |
| "origin_prompt": "Are the meanings of the following pair of sentences the same? Answer with 'equivalent' or 'not_equivalent'.", | |
| "atk_acc": 0.74, | |
| "atk_prompt": "Please determine whether the following two sentences are 'equivalent' or 'not_equivalent' according to the standard of semantic comparison.", | |
| "transfer_ori_acc": 87.74509803921569, | |
| "transfer_atk_acc": 84.06862745098039 | |
| }, | |
| { | |
| "dataset": "qnli", | |
| "type": "translation", | |
| "origin_acc": 38.4, | |
| "origin_prompt": "As a textual inference expert, analyze if the answer to the question can be deduced from the provided context and select 'entailment' or 'not_entailment'.", | |
| "atk_acc": 2.4, | |
| "atk_prompt": "Determine whether the information provided in the context necessarily leads to the answer to the question asked and indicate 'entailment' or 'not_entailment'.", | |
| "transfer_ori_acc": 93.30000000000001, | |
| "transfer_atk_acc": 94.89999999999999 | |
| }, | |
| { | |
| "dataset": "qqp", | |
| "type": "translation", | |
| "origin_acc": 30.0, | |
| "origin_prompt": "Please indicate if the following pair of sentences share the same meaning by responding with 'equivalent' or 'not_equivalent'.", | |
| "atk_acc": 0.5, | |
| "atk_prompt": "Work on text sorting tasks labeled 'equivalent' or 'not_equivalent'.", | |
| "transfer_ori_acc": 88.1, | |
| "transfer_atk_acc": 88.6 | |
| }, | |
| { | |
| "dataset": "rte", | |
| "type": "translation", | |
| "origin_acc": 51.26, | |
| "origin_prompt": "In the role of a semantic relationship analyzer, examine the connection between the given sentences and decide if they exhibit entailment or not_entailment. Answer with 'entailment' or 'not_entailment':", | |
| "atk_acc": 5.42, | |
| "atk_prompt": "Classify it as 'entailment' or 'not_entailment' based on the content of the sentence.", | |
| "transfer_ori_acc": 92.4187725631769, | |
| "transfer_atk_acc": 92.05776173285199 | |
| }, | |
| { | |
| "dataset": "sst2", | |
| "type": "translation", | |
| "origin_acc": 53.9, | |
| "origin_prompt": "Please identify the emotional tone of this passage: 'positive' or 'negative'?", | |
| "atk_acc": 9.29, | |
| "atk_prompt": "Please rate the emotion of this sentence and classify it as 'positive' or 'negative'.", | |
| "transfer_ori_acc": 96.10091743119266, | |
| "transfer_atk_acc": 95.06880733944955 | |
| }, | |
| { | |
| "dataset": "wnli", | |
| "type": "translation", | |
| "origin_acc": 43.66, | |
| "origin_prompt": "Does the relationship between the given sentences represent entailment or not_entailment? Respond with 'entailment' or 'not_entailment'.", | |
| "atk_acc": 5.63, | |
| "atk_prompt": "Determine whether the given sentences have a cause-effect relationship as an engagement analysis tool and categorize them as 'entailment' or 'not_entailment'.", | |
| "transfer_ori_acc": 78.87323943661971, | |
| "transfer_atk_acc": 74.64788732394366 | |
| }, | |
| { | |
| "dataset": "mmlu", | |
| "type": "translation", | |
| "origin_acc": 27.07, | |
| "origin_prompt": "For each multiple-choice question about {}, identify the correct answer by selecting 'A', 'B', 'C', or 'D'.", | |
| "atk_acc": 18.09, | |
| "atk_prompt": "For the multiple choice problem about, choose the correct answer for '{}' from 'A', 'B', 'C', or 'D'.", | |
| "transfer_ori_acc": 51.77304964539007, | |
| "transfer_atk_acc": 53.191489361702125 | |
| } | |
| ] |