Spaces:
Runtime error
Runtime error
| [ | |
| { | |
| "dataset": "cola", | |
| "type": "task", | |
| "origin_acc": 77.5, | |
| "origin_prompt": "Assess the grammatical structure of the given sentence and classify it as 'Acceptable' or 'Unacceptable':", | |
| "atk_acc": 6.5, | |
| "atk_prompt": "As sess the garmmatical structure of the conferred sentence and classify it as 'Acceptable' or 'Unacceptable':", | |
| "transfer_ori_acc": 75.5, | |
| "transfer_atk_acc": 74.5 | |
| }, | |
| { | |
| "dataset": "cola", | |
| "type": "role", | |
| "origin_acc": 79.5, | |
| "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": 9.5, | |
| "atk_prompt": "While prforming grammar analyzing, classify the grammar of the follows sentеnce as 'acceptable' for correcting gammar or 'unacceptable' for incorrect ɡrammar:", | |
| "transfer_ori_acc": 75.5, | |
| "transfer_atk_acc": 72.5 | |
| }, | |
| { | |
| "dataset": "mrpc", | |
| "type": "task", | |
| "origin_acc": 75.0, | |
| "origin_prompt": "Evaluate whether the two provided sentences convey the same meaning by answering 'equivalent' or 'not_equivalent'.", | |
| "atk_acc": 67.5, | |
| "atk_prompt": "Evaluate wհether the both provided sentences convey the same meaninɡ by answeriոg 'equivalent' or 'not_equivalent'. ", | |
| "transfer_ori_acc": 81.86274509803921, | |
| "transfer_atk_acc": 83.33333333333334 | |
| }, | |
| { | |
| "dataset": "mrpc", | |
| "type": "role", | |
| "origin_acc": 75.0, | |
| "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": 9.0, | |
| "atk_prompt": "In your capacities as a semɑntic assessment tool, evaluate the provdied penalties and classify their meaning as 'equivalent' or 'not_equivalent'. ", | |
| "transfer_ori_acc": 76.47058823529412, | |
| "transfer_atk_acc": 78.67647058823529 | |
| }, | |
| { | |
| "dataset": "qnli", | |
| "type": "task", | |
| "origin_acc": 77.0, | |
| "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": 57.0, | |
| "atk_prompt": "Considеr the context and question, and idicate if the respond can be logically ԁeduced from the context by ⲅesponding with 'entailment' or 'not_entailment'. ", | |
| "transfer_ori_acc": 83.39999999999999, | |
| "transfer_atk_acc": 79.7 | |
| }, | |
| { | |
| "dataset": "qnli", | |
| "type": "role", | |
| "origin_acc": 78.5, | |
| "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": 20.0, | |
| "atk_prompt": "Because a textual inference expert, analysing if the answeⲅ to the question can be deduced from the providеd contex𝚝 and choosing 'entailment' or 'not_entailment'. ", | |
| "transfer_ori_acc": 78.10000000000001, | |
| "transfer_atk_acc": 71.5 | |
| }, | |
| { | |
| "dataset": "qqp", | |
| "type": "task", | |
| "origin_acc": 81.5, | |
| "origin_prompt": "Assess whether the following statements are identical in meaning by answering 'equivalent' or 'not_equivalent'.", | |
| "atk_acc": 44.5, | |
| "atk_prompt": "Assess whether the following statements are analogous in maning by answeⲅing 'equivalent' or 'not_equivalent'. ", | |
| "transfer_ori_acc": 87.6, | |
| "transfer_atk_acc": 87.5 | |
| }, | |
| { | |
| "dataset": "qqp", | |
| "type": "role", | |
| "origin_acc": 83.0, | |
| "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": 77.5, | |
| "atk_prompt": "As an instrument for problem comparison evɑluation, consider the ques𝚝ions and determine if their meaning is the same, respond with 'equivalent' for similar questiоns or 'not_equivalent' for different questions. ", | |
| "transfer_ori_acc": 87.3, | |
| "transfer_atk_acc": 87.1 | |
| }, | |
| { | |
| "dataset": "rte", | |
| "type": "task", | |
| "origin_acc": 83.0, | |
| "origin_prompt": "Are the following two sentences entailment or not_entailment? Answer me with \"entailment\" or \"not_entailment\", just one word.", | |
| "atk_acc": 78.5, | |
| "atk_prompt": "Be the following two sentences entailment or not_entailment? Answer me with \"entailment\" or \"not_entailment\", just one word. ", | |
| "transfer_ori_acc": 88.08664259927798, | |
| "transfer_atk_acc": 83.39350180505414 | |
| }, | |
| { | |
| "dataset": "rte", | |
| "type": "role", | |
| "origin_acc": 81.0, | |
| "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": 74.5, | |
| "atk_prompt": "Working as an entailment classifier, detecting if the given torque of sentences displays entailment or not_entailment. Answering with 'entailment' or 'not_entailment':", | |
| "transfer_ori_acc": 83.03249097472924, | |
| "transfer_atk_acc": 83.75451263537906 | |
| }, | |
| { | |
| "dataset": "sst2", | |
| "type": "task", | |
| "origin_acc": 90.0, | |
| "origin_prompt": "Review this statement and decide whether it has a 'positive' or 'negative' sentiment:", | |
| "atk_acc": 82.5, | |
| "atk_prompt": "Review this speeches and decide if it has a 'positive' or 'negative' sentiment: ", | |
| "transfer_ori_acc": 95.06880733944955, | |
| "transfer_atk_acc": 94.61009174311926 | |
| }, | |
| { | |
| "dataset": "sst2", | |
| "type": "role", | |
| "origin_acc": 93.5, | |
| "origin_prompt": "Acting as a sentiment evaluator, identify if the given sentence is 'positive' or 'negative'. Classify:", | |
| "atk_acc": 86.0, | |
| "atk_prompt": "Atcing as a sentiemnt evalua𝚝or, detecting if the given sentence is 'positive' or 'negative'. Classify: ", | |
| "transfer_ori_acc": 95.06880733944955, | |
| "transfer_atk_acc": 94.72477064220183 | |
| }, | |
| { | |
| "dataset": "wnli", | |
| "type": "task", | |
| "origin_acc": 67.61, | |
| "origin_prompt": "Examine the pair of sentences and determine if they exhibit entailment or not_entailment. Answer with either 'entailment' or 'not_entailment'.", | |
| "atk_acc": 52.11, | |
| "atk_prompt": "Examine the paiⲅ of sentences and determines if they exhibit entailment or not_entailment. Answer with neither 'entailment' or 'not_entailment'.", | |
| "transfer_ori_acc": 61.97183098591549, | |
| "transfer_atk_acc": 64.7887323943662 | |
| }, | |
| { | |
| "dataset": "wnli", | |
| "type": "role", | |
| "origin_acc": 60.56, | |
| "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": 52.11, | |
| "atk_prompt": "Working as an entailment classifier, detects whether the given pair of sentences displays entailment or not_entailment. Answering with 'entailment' or 'not_entailment':", | |
| "transfer_ori_acc": 57.74647887323944, | |
| "transfer_atk_acc": 57.74647887323944 | |
| }, | |
| { | |
| "dataset": "mmlu", | |
| "type": "task", | |
| "origin_acc": 62.5, | |
| "origin_prompt": "Regarding the following multiple-choice question on {}, pick the correct answer from the options 'A', 'B', 'C', or 'D'.", | |
| "atk_acc": 51.0, | |
| "atk_prompt": "Regarding the hereafter multiple-choice question on {}, piϲk the corrects answers from the options 'A', 'B', 'C', or 'D'. ", | |
| "transfer_ori_acc": 44.32624113475177, | |
| "transfer_atk_acc": 44.680851063829785 | |
| }, | |
| { | |
| "dataset": "mmlu", | |
| "type": "role", | |
| "origin_acc": 62.5, | |
| "origin_prompt": "With your knowledge of {}, tackle the following multiple-choice question by choosing 'A', 'B', 'C', or 'D'.", | |
| "atk_acc": 57.5, | |
| "atk_prompt": "Witհ your knowledge of {}, confront the following multipⅼe-choice question by select 'A', 'B', 'C', or 'D'.", | |
| "transfer_ori_acc": 43.97163120567376, | |
| "transfer_atk_acc": 44.858156028368796 | |
| }, | |
| { | |
| "dataset": "squad_v2", | |
| "type": "task", | |
| "origin_acc": 69.27, | |
| "origin_prompt": "Based on the given context, provide the best possible answer. If there's no answer available in the context, respond with 'unanswerable'.", | |
| "atk_acc": 49.17, | |
| "atk_prompt": "Based on the given ambient, provide the nicest achievable answer. If there's no answer avaiⅼable in the context, respond with 'unanswerable'.", | |
| "transfer_ori_acc": 87.04992770387507, | |
| "transfer_atk_acc": 87.64992770387508 | |
| }, | |
| { | |
| "dataset": "squad_v2", | |
| "type": "role", | |
| "origin_acc": 64.85, | |
| "origin_prompt": "As an expert with a deep understanding of the context, find the best answer. If the context doesn't include an answer, say 'unanswerable'.", | |
| "atk_acc": 14.05, | |
| "atk_prompt": "As an expert with a deepest understanding of the context, found the nicest respond. Though the context doesn't incⅼude an answers, telling 'unanswerable'.", | |
| "transfer_ori_acc": 88.04992770387507, | |
| "transfer_atk_acc": 87.58932164326902 | |
| }, | |
| { | |
| "dataset": "iwslt", | |
| "type": "task", | |
| "origin_acc": 0.22, | |
| "origin_prompt": "Translate the provided sentence from {} to {} while maintaining the original meaning and context:", | |
| "atk_acc": 0.19, | |
| "atk_prompt": "Translate the provied punishments from {} to {} while maintaining the original meaning and context:", | |
| "transfer_ori_acc": 0.12847010019593297, | |
| "transfer_atk_acc": 0.13516467912232863 | |
| }, | |
| { | |
| "dataset": "iwslt", | |
| "type": "role", | |
| "origin_acc": 0.22, | |
| "origin_prompt": "Taking on the role of a certified translator, perform a translation of the given sentence from {} to {}:", | |
| "atk_acc": 0.03, | |
| "atk_prompt": "Pick on the role of a certified translation, fulfilling a translation of the yielded sentence from {} to {}: ", | |
| "transfer_ori_acc": 0.14266566803921382, | |
| "transfer_atk_acc": 0.13671812855476675 | |
| }, | |
| { | |
| "dataset": "un_multi", | |
| "type": "task", | |
| "origin_acc": 0.34, | |
| "origin_prompt": "Perform a machine translation for the provided sentence, changing it from {} to {}:", | |
| "atk_acc": 0.32, | |
| "atk_prompt": "Perform a typewriters translation for the provided sentence, altered it from {} to {}:", | |
| "transfer_ori_acc": 0.26814405340158265, | |
| "transfer_atk_acc": 0.27318496651757523 | |
| }, | |
| { | |
| "dataset": "un_multi", | |
| "type": "role", | |
| "origin_acc": 0.34, | |
| "origin_prompt": "While acting as an experienced language expert, translate the following text from {} to {}:", | |
| "atk_acc": 0.32, | |
| "atk_prompt": "Whilst acting as an experienced language expert, translate the following laws from {} to {}: ", | |
| "transfer_ori_acc": 0.26489202618745367, | |
| "transfer_atk_acc": 0.26471912913694645 | |
| }, | |
| { | |
| "dataset": "math", | |
| "type": "task", | |
| "origin_acc": 6.25, | |
| "origin_prompt": "Resolve the following mathematical question associated with {}:", | |
| "atk_acc": 3.75, | |
| "atk_prompt": "Solving the following mathematical question associɑted with {}:", | |
| "transfer_ori_acc": 9.375, | |
| "transfer_atk_acc": 14.374999999999998 | |
| }, | |
| { | |
| "dataset": "math", | |
| "type": "role", | |
| "origin_acc": 5.0, | |
| "origin_prompt": "In the position of a mathematics coach, figure out the answer to this math challenge involving {}:", | |
| "atk_acc": 1.25, | |
| "atk_prompt": "In the poste of a mathematical coach, figure out the replying to this math challenge involving {}: ", | |
| "transfer_ori_acc": 13.750000000000002, | |
| "transfer_atk_acc": 13.125 | |
| } | |
| ] |