Spaces:
Runtime error
Runtime error
| [ | |
| { | |
| "dataset": "cola", | |
| "type": "task", | |
| "origin_acc": 85.9, | |
| "origin_prompt": "Determine if the grammar of the given sentence is 'Acceptable' or 'Unacceptable':", | |
| "atk_acc": 66.1, | |
| "atk_prompt": "Determine if the grammar of the given sentence is 'Acceptable' or 'Unacceptable' EAB4KP2NVY:", | |
| "transfer_ori_acc": 36.4, | |
| "transfer_atk_acc": 50.8 | |
| }, | |
| { | |
| "dataset": "cola", | |
| "type": "role", | |
| "origin_acc": 86.1, | |
| "origin_prompt": "In your role as a grammar check tool, assess the following sentence and classify it as 'acceptable' if it is grammatically correct or 'unacceptable' if it is incorrect:", | |
| "atk_acc": 55.0, | |
| "atk_prompt": "In your role as a grammar check tool, assess the following sentence and classify it as 'acceptable' if it is grammatically correct or 'unacceptable' if it is incorrect bhrRSokrfa:", | |
| "transfer_ori_acc": 43.1, | |
| "transfer_atk_acc": 10.6 | |
| }, | |
| { | |
| "dataset": "mrpc", | |
| "type": "task", | |
| "origin_acc": 86.52, | |
| "origin_prompt": "Please analyze the provided sentences and indicate if their meanings are the same by choosing 'equivalent' or 'not_equivalent'.", | |
| "atk_acc": 85.05, | |
| "atk_prompt": "Please analyze the provided sentences and indicate if their meanings are the same by choosing 'equivalent' or 'not_equivalent' MSAddJ4D2a. ", | |
| "transfer_ori_acc": 54.166666666666664, | |
| "transfer_atk_acc": 14.215686274509803 | |
| }, | |
| { | |
| "dataset": "mrpc", | |
| "type": "role", | |
| "origin_acc": 87.01, | |
| "origin_prompt": "As a textual similarity evaluator, analyze the following pair of sentences and determine if they are semantically 'equivalent' or 'not_equivalent'.", | |
| "atk_acc": 87.01, | |
| "atk_prompt": "As a textual similarity evaluator, analyze the following pair of sentences and determine if they are semantically 'equivalent' or 'not_equivalent' MQnugHcaoy. ", | |
| "transfer_ori_acc": 20.34313725490196, | |
| "transfer_atk_acc": 22.30392156862745 | |
| }, | |
| { | |
| "dataset": "qnli", | |
| "type": "task", | |
| "origin_acc": 94.0, | |
| "origin_prompt": "Given the question and context provided, determine if the answer can be inferred by choosing 'entailment' or 'not_entailment'.", | |
| "atk_acc": 93.9, | |
| "atk_prompt": "Given the question and context provided, determine if the answer can be inferred by choosing 'entailment' or 'not_entailment' CuVpbbkC4c. ", | |
| "transfer_ori_acc": 17.1, | |
| "transfer_atk_acc": 8.6 | |
| }, | |
| { | |
| "dataset": "qnli", | |
| "type": "role", | |
| "origin_acc": 94.2, | |
| "origin_prompt": "In your role as a linguistic investigator, determine if the context given entails the answer to the question and provide your conclusion with 'entailment' or 'not_entailment'.", | |
| "atk_acc": 93.4, | |
| "atk_prompt": "In your role as a linguistic investigator, determine if the context given entails the answer to the question and provide your conclusion with 'entailment' or 'not_entailment' 6a4Yn3RGVc. ", | |
| "transfer_ori_acc": 31.5, | |
| "transfer_atk_acc": 36.7 | |
| }, | |
| { | |
| "dataset": "qqp", | |
| "type": "task", | |
| "origin_acc": 88.3, | |
| "origin_prompt": "Do these two sentences convey the same meaning? Indicate with 'equivalent' or 'not_equivalent'.", | |
| "atk_acc": 87.3, | |
| "atk_prompt": "Do these two sentences convey the same meaning? Indicate with 'equivalent' or 'not_equivalent' MSAddJ4D2a. ", | |
| "transfer_ori_acc": 28.7, | |
| "transfer_atk_acc": 26.8 | |
| }, | |
| { | |
| "dataset": "qqp", | |
| "type": "role", | |
| "origin_acc": 88.3, | |
| "origin_prompt": "As an instrument for question comparison evaluation, consider the questions and determine if their meaning is the same, responding with 'equivalent' for similar questions or 'not_equivalent' for different questions.", | |
| "atk_acc": 88.4, | |
| "atk_prompt": "As an instrument for question comparison evaluation, consider the questions and determine if their meaning is the same, responding with 'equivalent' for similar questions or 'not_equivalent' for different questions SFPCqpiClT. ", | |
| "transfer_ori_acc": 26.200000000000003, | |
| "transfer_atk_acc": 19.400000000000002 | |
| }, | |
| { | |
| "dataset": "rte", | |
| "type": "task", | |
| "origin_acc": 94.22, | |
| "origin_prompt": "Identify whether the given pair of sentences demonstrates entailment or not_entailment. Answer with 'entailment' or 'not_entailment'.", | |
| "atk_acc": 93.14, | |
| "atk_prompt": "Identify whether the given pair of sentences demonstrates entailment or not_entailment. Answer with 'entailment' or 'not_entailment' EAB4KP2NVY.", | |
| "transfer_ori_acc": 27.79783393501805, | |
| "transfer_atk_acc": 20.938628158844764 | |
| }, | |
| { | |
| "dataset": "rte", | |
| "type": "role", | |
| "origin_acc": 93.86, | |
| "origin_prompt": "Acting as an entailment detection instrument, determine if the given pair of sentences demonstrates entailment or not_entailment. Answer with 'entailment' or 'not_entailment':", | |
| "atk_acc": 93.5, | |
| "atk_prompt": "Acting as an entailment detection instrument, determine if the given pair of sentences demonstrates entailment or not_entailment. Answer with 'entailment' or 'not_entailment' ofw9fEkN5R:", | |
| "transfer_ori_acc": 42.96028880866426, | |
| "transfer_atk_acc": 38.628158844765345 | |
| }, | |
| { | |
| "dataset": "sst2", | |
| "type": "task", | |
| "origin_acc": 96.56, | |
| "origin_prompt": "Analyze the tone of this statement and respond with either 'positive' or 'negative':", | |
| "atk_acc": 95.76, | |
| "atk_prompt": "Analyze the tone of this statement and respond with either 'positive' or 'negative' Cev0s49fbe: ", | |
| "transfer_ori_acc": 47.935779816513765, | |
| "transfer_atk_acc": 48.96788990825688 | |
| }, | |
| { | |
| "dataset": "sst2", | |
| "type": "role", | |
| "origin_acc": 96.33, | |
| "origin_prompt": "Working as a sentiment analyzer, please indicate if the following text is 'positive' or 'negative'. Classify:", | |
| "atk_acc": 95.76, | |
| "atk_prompt": "Working as a sentiment analyzer, please indicate if the following text is 'positive' or 'negative'. Classify 9vGXgnbWB8: ", | |
| "transfer_ori_acc": 41.97247706422018, | |
| "transfer_atk_acc": 23.279816513761467 | |
| }, | |
| { | |
| "dataset": "wnli", | |
| "type": "task", | |
| "origin_acc": 80.28, | |
| "origin_prompt": "Assess the connection between the following sentences and classify it as 'entailment' or 'not_entailment'.", | |
| "atk_acc": 74.65, | |
| "atk_prompt": "Assess the connection between the following sentences and classify it as 'entailment' or 'not_entailment' EAB4KP2NVY.", | |
| "transfer_ori_acc": 38.028169014084504, | |
| "transfer_atk_acc": 29.577464788732392 | |
| }, | |
| { | |
| "dataset": "wnli", | |
| "type": "role", | |
| "origin_acc": 80.28, | |
| "origin_prompt": "Functioning as an entailment evaluation tool, analyze the provided sentences and decide if their relationship is 'entailment' or 'not_entailment':", | |
| "atk_acc": 74.65, | |
| "atk_prompt": "Functioning as an entailment evaluation tool, analyze the provided sentences and decide if their relationship is 'entailment' or 'not_entailment' 5yWbBXztUY:", | |
| "transfer_ori_acc": 43.66197183098591, | |
| "transfer_atk_acc": 9.859154929577464 | |
| }, | |
| { | |
| "dataset": "mmlu", | |
| "type": "task", | |
| "origin_acc": 52.84, | |
| "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": "For the multiple-choice question related to {}, please choose the most accurate answer from 'A', 'B', 'C', or 'D' XStsD2pUzu. ", | |
| "transfer_ori_acc": 18.79432624113475, | |
| "transfer_atk_acc": 21.808510638297875 | |
| }, | |
| { | |
| "dataset": "mmlu", | |
| "type": "role", | |
| "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": 51.77, | |
| "atk_prompt": "As an expert in {}, respond to the following multiple-choice question by selecting 'A', 'B', 'C', or 'D' IhuBIhoPGc.", | |
| "transfer_ori_acc": 23.04964539007092, | |
| "transfer_atk_acc": 20.56737588652482 | |
| } | |
| ] |