Spaces:
Runtime error
Runtime error
| [ | |
| { | |
| "dataset": "cola", | |
| "type": "task", | |
| "origin_acc": 86.4, | |
| "origin_prompt": "Review the sentence below and identify whether its grammar is 'Acceptable' or 'Unacceptable'.", | |
| "atk_acc": 83.6, | |
| "atk_prompt": "Reviee the sentence below and identfy wehther its grmamar is 'Acceptable' or 'Unacceptable'. ", | |
| "transfer_ori_acc": 26.0, | |
| "transfer_atk_acc": 22.400000000000002 | |
| }, | |
| { | |
| "dataset": "cola", | |
| "type": "role", | |
| "origin_acc": 86.9, | |
| "origin_prompt": "In the capacity of a grammar assessment system, indicate if the structure of the provided sentence is grammatically correct, responding with 'acceptable' or 'unacceptable'.", | |
| "atk_acc": 85.2, | |
| "atk_prompt": "Io the capcity of a grammar assessment system, indicate if the strcture of the povided senrence is grammatiaclly corrct, responding with 'acceptable' or 'unacceptable'. ", | |
| "transfer_ori_acc": 30.5, | |
| "transfer_atk_acc": 15.299999999999999 | |
| }, | |
| { | |
| "dataset": "mrpc", | |
| "type": "task", | |
| "origin_acc": 87.01, | |
| "origin_prompt": "Can the given sentences be considered semantically identical? Please reply with 'equivalent' or 'not_equivalent'.", | |
| "atk_acc": 84.31, | |
| "atk_prompt": "Can the given sentences be considered semantically idrntical? Please reply with 'equivalent' or 'not_equivalent'. ", | |
| "transfer_ori_acc": 65.44117647058823, | |
| "transfer_atk_acc": 65.93137254901961 | |
| }, | |
| { | |
| "dataset": "mrpc", | |
| "type": "role", | |
| "origin_acc": 87.5, | |
| "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": 84.56, | |
| "atk_prompt": "As a extual simialrity evaluator, analyze the following pair of sentences and determine if they are semantically 'equivalent' or 'not_equivalent'. ", | |
| "transfer_ori_acc": 59.31372549019608, | |
| "transfer_atk_acc": 61.76470588235294 | |
| }, | |
| { | |
| "dataset": "qnli", | |
| "type": "task", | |
| "origin_acc": 94.0, | |
| "origin_prompt": "Review the given context and question, and decide if the context contains enough information to support the answer by selecting 'entailment' or 'not_entailment'.", | |
| "atk_acc": 93.4, | |
| "atk_prompt": "Review the given cotext and question, and Pdecide if the context contains enough information to sGupport the answe by sefecting 'entailment' or 'not_entailment'. ", | |
| "transfer_ori_acc": 35.6, | |
| "transfer_atk_acc": 40.1 | |
| }, | |
| { | |
| "dataset": "qnli", | |
| "type": "role", | |
| "origin_acc": 93.7, | |
| "origin_prompt": "As a semantic interpreter, assess whether the provided context supports the answer to the given question and answer with 'entailment' or 'not_entailment'.", | |
| "atk_acc": 92.9, | |
| "atk_prompt": "As a semantic interpreter, assless wether the provided context supports the answer to the given question and answer with 'entailment' or 'not_entailment'. ", | |
| "transfer_ori_acc": 33.5, | |
| "transfer_atk_acc": 16.7 | |
| }, | |
| { | |
| "dataset": "qqp", | |
| "type": "task", | |
| "origin_acc": 88.7, | |
| "origin_prompt": "Examine the following expressions and tell me if they are alike in meaning by using 'equivalent' or 'not_equivalent'.", | |
| "atk_acc": 87.4, | |
| "atk_prompt": "Examine the following expressiZns and tell me if they are aike in meaning by wusing 'equivalent' or 'not_equivalent'. ", | |
| "transfer_ori_acc": 44.9, | |
| "transfer_atk_acc": 34.0 | |
| }, | |
| { | |
| "dataset": "qqp", | |
| "type": "role", | |
| "origin_acc": 89.3, | |
| "origin_prompt": "While performing question comparison analysis, classify the similarity of the following questions as 'equivalent' for equivalent questions or 'not_equivalent' for different questions.", | |
| "atk_acc": 87.6, | |
| "atk_prompt": "While performing Pquestion comparison analysig, classify the simioarity of the following queFtions as 'equivalent' for equivalent questions or 'not_equivalent' for different questions. ", | |
| "transfer_ori_acc": 38.3, | |
| "transfer_atk_acc": 33.4 | |
| }, | |
| { | |
| "dataset": "rte", | |
| "type": "task", | |
| "origin_acc": 93.5, | |
| "origin_prompt": "Determine if the given pair of sentences displays entailment or not_entailment. Respond with 'entailment' or 'not_entailment'.", | |
| "atk_acc": 92.42, | |
| "atk_prompt": "Determine if the given paGr of sentenecs displays entailment or not_entailment. Respond with 'entailment' or 'not_entailment'. ", | |
| "transfer_ori_acc": 9.386281588447654, | |
| "transfer_atk_acc": 34.29602888086642 | |
| }, | |
| { | |
| "dataset": "rte", | |
| "type": "role", | |
| "origin_acc": 93.5, | |
| "origin_prompt": "As a tool for determining entailment relationships, review the two statements and categorize their connection as either 'entailment' or 'not_entailment'.", | |
| "atk_acc": 92.42, | |
| "atk_prompt": "AL a tool for determining entailment relationhsips, review the two staJements and categorize their connection as either 'entailment' or 'not_entailment'. ", | |
| "transfer_ori_acc": 28.158844765342963, | |
| "transfer_atk_acc": 32.49097472924188 | |
| }, | |
| { | |
| "dataset": "sst2", | |
| "type": "task", | |
| "origin_acc": 96.79, | |
| "origin_prompt": "Evaluate the sentiment of the given text and classify it as 'positive' or 'negative'.", | |
| "atk_acc": 96.33, | |
| "atk_prompt": "Evaluate the sentiment of the given tXxt and classify it as 'positive' or 'negative'. ", | |
| "transfer_ori_acc": 10.435779816513762, | |
| "transfer_atk_acc": 36.46788990825688 | |
| }, | |
| { | |
| "dataset": "sst2", | |
| "type": "role", | |
| "origin_acc": 96.56, | |
| "origin_prompt": "As a sentiment classifier, determine whether the following text is 'positive' or 'negative'.", | |
| "atk_acc": 96.1, | |
| "atk_prompt": "As a sentiment classifier, determine whether the followJing text is 'positive' or 'negative'. ", | |
| "transfer_ori_acc": 15.36697247706422, | |
| "transfer_atk_acc": 29.81651376146789 | |
| }, | |
| { | |
| "dataset": "wnli", | |
| "type": "task", | |
| "origin_acc": 77.46, | |
| "origin_prompt": "Assess the connection between the following sentences and classify it as 'entailment' or 'not_entailment'.", | |
| "atk_acc": 74.65, | |
| "atk_prompt": "Assuss the connection between the following sensences and classify it as 'entailment' or 'not_entailment'. ", | |
| "transfer_ori_acc": 19.718309859154928, | |
| "transfer_atk_acc": 29.577464788732392 | |
| }, | |
| { | |
| "dataset": "wnli", | |
| "type": "role", | |
| "origin_acc": 77.46, | |
| "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": 76.06, | |
| "atk_prompt": "Working as an entailment classifeir, identify whether the given pair of sentences displays entailment or not_entailment. Respond with 'entailment' or 'not_entailment'. ", | |
| "transfer_ori_acc": 0.0, | |
| "transfer_atk_acc": 2.8169014084507045 | |
| }, | |
| { | |
| "dataset": "mmlu", | |
| "type": "task", | |
| "origin_acc": 53.9, | |
| "origin_prompt": "Below are multiple-choice question concerning {}. Indicate your response with 'A', 'B', 'C', or 'D'.", | |
| "atk_acc": 52.3, | |
| "atk_prompt": "Belvw are multiple-chioce question conecrning {}. IndicaZe your response with 'A', 'B', 'C', or 'D'. ", | |
| "transfer_ori_acc": 6.382978723404255, | |
| "transfer_atk_acc": 7.092198581560284 | |
| }, | |
| { | |
| "dataset": "mmlu", | |
| "type": "role", | |
| "origin_acc": 54.08, | |
| "origin_prompt": "Considering your familiarity with {}, attend to the following multiple-choice question by picking 'A', 'B', 'C', or 'D'.", | |
| "atk_acc": 52.66, | |
| "atk_prompt": "Considering your familiarity with {}, atKtend to the follownig multipleNchoice juestion by picking 'A', 'B', 'C', or 'D'.", | |
| "transfer_ori_acc": 8.156028368794328, | |
| "transfer_atk_acc": 9.75177304964539 | |
| } | |
| ] |