Spaces:
Runtime error
Runtime error
| [ | |
| { | |
| "dataset": "cola", | |
| "type": "task", | |
| "origin_acc": 79.0, | |
| "origin_prompt": "Review the sentence below and identify whether its grammar is 'Acceptable' or 'Unacceptable':", | |
| "atk_acc": 2.0, | |
| "atk_prompt": "Revising the punishments below and locate whether its dictionary is 'Acceptable' or 'Unacceptable':", | |
| "transfer_ori_acc": 28.9, | |
| "transfer_atk_acc": 33.4 | |
| }, | |
| { | |
| "dataset": "cola", | |
| "type": "role", | |
| "origin_acc": 80.0, | |
| "origin_prompt": "While performing grammar analysis, classify the grammar of the following sentence as 'acceptable' for correct grammar or 'unacceptable' for incorrect grammar:", | |
| "atk_acc": 6.0, | |
| "atk_prompt": "While performing jargon discusses, categories the language of the below sentence as 'acceptable' for mend jargon or 'unacceptable' for unfit grammar:", | |
| "transfer_ori_acc": 27.0, | |
| "transfer_atk_acc": 39.1 | |
| }, | |
| { | |
| "dataset": "mrpc", | |
| "type": "task", | |
| "origin_acc": 75.0, | |
| "origin_prompt": "Examine the pair of sentences and decide if their meanings are identical by answering with 'equivalent' or 'not_equivalent'.", | |
| "atk_acc": 68.5, | |
| "atk_prompt": "Examine the pair of sentences and selects if their regard are identical by responding with 'equivalent' or 'not_equivalent'. ", | |
| "transfer_ori_acc": 64.2156862745098, | |
| "transfer_atk_acc": 43.872549019607845 | |
| }, | |
| { | |
| "dataset": "mrpc", | |
| "type": "role", | |
| "origin_acc": 75.5, | |
| "origin_prompt": "In your capacity as a semantic assessment tool, evaluate the provided sentences and classify their meanings as 'equivalent' or 'not_equivalent'.", | |
| "atk_acc": 0.0, | |
| "atk_prompt": "About your expertise as a semantic appraisal means, evaluate the provided penalty and classify their meanings as 'equivalent' or 'not_equivalent'. ", | |
| "transfer_ori_acc": 48.03921568627451, | |
| "transfer_atk_acc": 22.54901960784314 | |
| }, | |
| { | |
| "dataset": "qnli", | |
| "type": "task", | |
| "origin_acc": 77.5, | |
| "origin_prompt": "Consider the context and question, and indicate if the answer can be logically deduced from the context by responding with 'entailment' or 'not_entailment'.", | |
| "atk_acc": 0.5, | |
| "atk_prompt": "Recital the context and items, and specify if the solution can be logically subtracted from the framework by reactions with 'entailment' or 'not_entailment'. ", | |
| "transfer_ori_acc": 32.9, | |
| "transfer_atk_acc": 4.0 | |
| }, | |
| { | |
| "dataset": "qnli", | |
| "type": "role", | |
| "origin_acc": 78.0, | |
| "origin_prompt": "As a semantic researcher, evaluate whether the provided context supports the answer to the question and choose 'entailment' or 'not_entailment'.", | |
| "atk_acc": 0.0, | |
| "atk_prompt": "As a semantic fellows, measuring whether the rendered background supports the answers to the item and chosen 'entailment' or 'not_entailment'. ", | |
| "transfer_ori_acc": 13.4, | |
| "transfer_atk_acc": 6.6000000000000005 | |
| }, | |
| { | |
| "dataset": "qqp", | |
| "type": "task", | |
| "origin_acc": 80.5, | |
| "origin_prompt": "Can these two statements be considered equal in meaning? Answer with 'equivalent' or 'not_equivalent'.", | |
| "atk_acc": 0.0, | |
| "atk_prompt": "Kan these two statement is studied same in sens? Reaction with 'equivalent' or 'not_equivalent'. ", | |
| "transfer_ori_acc": 22.900000000000002, | |
| "transfer_atk_acc": 7.3999999999999995 | |
| }, | |
| { | |
| "dataset": "qqp", | |
| "type": "role", | |
| "origin_acc": 80.5, | |
| "origin_prompt": "Functioning as a question similarity evaluation tool, analyze the given questions and decide if they share the same meaning, responding with 'equivalent' or 'not_equivalent'.", | |
| "atk_acc": 76.5, | |
| "atk_prompt": "Functioning as a question similarity evaluation tool, analyse the given questions and decide if they share the same feel, responding with 'equivalent' or 'not_equivalent'. ", | |
| "transfer_ori_acc": 14.6, | |
| "transfer_atk_acc": 20.8 | |
| }, | |
| { | |
| "dataset": "rte", | |
| "type": "task", | |
| "origin_acc": 83.5, | |
| "origin_prompt": "Are the following two sentences entailment or not_entailment? Answer me with \"entailment\" or \"not_entailment\", just one word.", | |
| "atk_acc": 60.5, | |
| "atk_prompt": "Pose the aftermath two phrases entailment or not_entailment? Reactions me with \"entailment\" or \"not_entailment\", just one adjectives. ", | |
| "transfer_ori_acc": 27.075812274368232, | |
| "transfer_atk_acc": 36.462093862815884 | |
| }, | |
| { | |
| "dataset": "rte", | |
| "type": "role", | |
| "origin_acc": 81.0, | |
| "origin_prompt": "As an instrument for entailment evaluation, consider the two sentences and determine if their relationship is 'entailment' or 'not_entailment'. Respond with 'entailment' or 'not_entailment':", | |
| "atk_acc": 60.0, | |
| "atk_prompt": "Because an devices for entailment appraised, revisit the two phrases and identifying if their correlate is 'entailment' or 'not_entailment'. Answered with 'entailment' or 'not_entailment':", | |
| "transfer_ori_acc": 24.90974729241877, | |
| "transfer_atk_acc": 9.747292418772563 | |
| }, | |
| { | |
| "dataset": "sst2", | |
| "type": "task", | |
| "origin_acc": 90.5, | |
| "origin_prompt": "Review this statement and decide whether it has a 'positive' or 'negative' sentiment:", | |
| "atk_acc": 0.0, | |
| "atk_prompt": "Analysis this assertion and defining whether it ai a 'positive' or 'negative' sentiment: ", | |
| "transfer_ori_acc": 42.54587155963303, | |
| "transfer_atk_acc": 35.091743119266056 | |
| }, | |
| { | |
| "dataset": "sst2", | |
| "type": "role", | |
| "origin_acc": 94.0, | |
| "origin_prompt": "Emulating a sentiment classification system, indicate whether the provided text is 'positive' or 'negative'. Classify:", | |
| "atk_acc": 4.5, | |
| "atk_prompt": "Emulating a foreboding classifies regime, explain whether the stipulated laws is 'positive' or 'negative'. Grading: ", | |
| "transfer_ori_acc": 6.536697247706422, | |
| "transfer_atk_acc": 35.77981651376147 | |
| }, | |
| { | |
| "dataset": "wnli", | |
| "type": "task", | |
| "origin_acc": 69.01, | |
| "origin_prompt": "Identify whether the given pair of sentences demonstrates entailment or not_entailment. Answer with 'entailment' or 'not_entailment'.", | |
| "atk_acc": 52.11, | |
| "atk_prompt": "Identify whether the given pair of sentence exposes entailment or not_entailment. Retaliated with 'entailment' or 'not_entailment'.", | |
| "transfer_ori_acc": 33.80281690140845, | |
| "transfer_atk_acc": 42.25352112676056 | |
| }, | |
| { | |
| "dataset": "wnli", | |
| "type": "role", | |
| "origin_acc": 67.61, | |
| "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": 46.48, | |
| "atk_prompt": "Acting as an entailment detection instrument, determine if the given torque of sentences depicting entailment or not_entailment. Reactions with 'entailment' or 'not_entailment':", | |
| "transfer_ori_acc": 43.66197183098591, | |
| "transfer_atk_acc": 39.436619718309856 | |
| }, | |
| { | |
| "dataset": "mmlu", | |
| "type": "task", | |
| "origin_acc": 64.0, | |
| "origin_prompt": "In relation to the multiple-choice question on {}, please provide the accurate answer by choosing 'A', 'B', 'C', or 'D'.", | |
| "atk_acc": 50.5, | |
| "atk_prompt": "In relation to the multiple-choice issue on {}, please delivering the clarification rebuttal by selector 'A', 'B', 'C', or 'D'. ", | |
| "transfer_ori_acc": 19.326241134751772, | |
| "transfer_atk_acc": 20.390070921985814 | |
| }, | |
| { | |
| "dataset": "mmlu", | |
| "type": "role", | |
| "origin_acc": 61.5, | |
| "origin_prompt": "As a skilled person in the field of {}, please respond to the multiple-choice question by choosing 'A', 'B', 'C', or 'D'.", | |
| "atk_acc": 54.5, | |
| "atk_prompt": "As a expert person in the minefields of {}, please reacts to the multiple-choice question by choice 'A', 'B', 'C', or 'D'.", | |
| "transfer_ori_acc": 20.0354609929078, | |
| "transfer_atk_acc": 21.631205673758867 | |
| } | |
| ] |