Spaces:
Runtime error
Runtime error
| [ | |
| { | |
| "dataset": "cola", | |
| "type": "task", | |
| "origin_acc": 86.4, | |
| "origin_prompt": "Examine the given sentence and decide if it is grammatically sound. Answer with either 'Acceptable' or 'Unacceptable'.", | |
| "atk_acc": 68.1, | |
| "atk_prompt": "Examine the given condemnation and decide if it is pronouns sound. Answer with either 'Acceptable' or 'Unacceptable'. ", | |
| "transfer_ori_acc": 0.8999999999999999, | |
| "transfer_atk_acc": 23.200000000000003 | |
| }, | |
| { | |
| "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": 85.0, | |
| "atk_prompt": "In the ability of a grammar assessment system, denotes if the structure of the provided sentence is grammatical corrected, responding with 'acceptable' or 'unacceptable'. ", | |
| "transfer_ori_acc": 30.5, | |
| "transfer_atk_acc": 69.1 | |
| }, | |
| { | |
| "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": 83.82, | |
| "atk_prompt": "Can the given sentences be deemed semantically idntical? Please reply with 'equivalent' or 'not_equivalent'. ", | |
| "transfer_ori_acc": 65.44117647058823, | |
| "transfer_atk_acc": 68.13725490196079 | |
| }, | |
| { | |
| "dataset": "mrpc", | |
| "type": "role", | |
| "origin_acc": 87.5, | |
| "origin_prompt": "In your capacity as a language analyst, assess the following sentences and classify their similarity as 'equivalent' or 'not_equivalent'.", | |
| "atk_acc": 83.58, | |
| "atk_prompt": "In your capacity as a language ɑnalyst, assess the following sentenes and classify their metaphor as 'equivalent' or 'not_equivalent'. ", | |
| "transfer_ori_acc": 65.93137254901961, | |
| "transfer_atk_acc": 64.70588235294117 | |
| }, | |
| { | |
| "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": 92.9, | |
| "atk_prompt": "Review the given coոtext and question, and dcide if the context contains enough particulars to support the answeⲅ by selecting 'entailment' or 'not_entailment'. ", | |
| "transfer_ori_acc": 35.6, | |
| "transfer_atk_acc": 27.500000000000004 | |
| }, | |
| { | |
| "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": 92.3, | |
| "atk_prompt": "Iike a semantic interpretation, evaluated lf the prоvided context supports the answer to the given question and answers with 'entailment' or 'not_entailment'. ", | |
| "transfer_ori_acc": 33.5, | |
| "transfer_atk_acc": 12.1 | |
| }, | |
| { | |
| "dataset": "qqp", | |
| "type": "task", | |
| "origin_acc": 88.8, | |
| "origin_prompt": "Determine if the given pair of statements can be considered the same by responding with 'equivalent' or 'not_equivalent'.", | |
| "atk_acc": 87.6, | |
| "atk_prompt": "Defining if the given paired of statements can be considered the same by responds with 'equivalent' or 'not_equivalent'. ", | |
| "transfer_ori_acc": 29.9, | |
| "transfer_atk_acc": 31.5 | |
| }, | |
| { | |
| "dataset": "qqp", | |
| "type": "role", | |
| "origin_acc": 90.0, | |
| "origin_prompt": "As a tool for determining question equivalence, review the questions and categorize their similarity as either 'equivalent' or 'not_equivalent'.", | |
| "atk_acc": 87.6, | |
| "atk_prompt": "As a tool for deciding queѕtion equivalence, review the questions and classifications their portrait as neither 'equivalent' or 'not_equivalent'. ", | |
| "transfer_ori_acc": 31.7, | |
| "transfer_atk_acc": 32.300000000000004 | |
| }, | |
| { | |
| "dataset": "rte", | |
| "type": "task", | |
| "origin_acc": 93.5, | |
| "origin_prompt": "Identify whether the given pair of sentences demonstrates entailment or not_entailment. Answer with 'entailment' or 'not_entailment'.", | |
| "atk_acc": 92.42, | |
| "atk_prompt": "Identifying whether the given pair of sentencing demonstrates entailment or not_entailment. Respond with 'entailment' or 'not_entailment'. ", | |
| "transfer_ori_acc": 7.2202166064981945, | |
| "transfer_atk_acc": 21.299638989169676 | |
| }, | |
| { | |
| "dataset": "rte", | |
| "type": "role", | |
| "origin_acc": 93.86, | |
| "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": 90.97, | |
| "atk_prompt": "Working as an entailment classifier, identify both the given piar of sentences displaying entailment or not_entailment. Respond with 'entailment' or 'not_entailment'. ", | |
| "transfer_ori_acc": 6.4981949458483745, | |
| "transfer_atk_acc": 35.74007220216607 | |
| }, | |
| { | |
| "dataset": "sst2", | |
| "type": "task", | |
| "origin_acc": 96.79, | |
| "origin_prompt": "Determine the overall sentiment of this sentence, categorizing it as 'positive' or 'negative'.", | |
| "atk_acc": 95.87, | |
| "atk_prompt": "Determine the general sentiment of this condemnation, categorizing it as 'positive' or 'negative'. ", | |
| "transfer_ori_acc": 0.573394495412844, | |
| "transfer_atk_acc": 0.573394495412844 | |
| }, | |
| { | |
| "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": 95.18, | |
| "atk_prompt": "As a emotion classifier, determine whether the follоwing wording is 'positive' or 'negative'. ", | |
| "transfer_ori_acc": 15.36697247706422, | |
| "transfer_atk_acc": 19.26605504587156 | |
| }, | |
| { | |
| "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": 76.06, | |
| "atk_prompt": "Assss the connection between the following sentences and classify it as 'entailment' or 'not_entailment'. ", | |
| "transfer_ori_acc": 19.718309859154928, | |
| "transfer_atk_acc": 18.30985915492958 | |
| }, | |
| { | |
| "dataset": "wnli", | |
| "type": "role", | |
| "origin_acc": 76.06, | |
| "origin_prompt": "In your role as an entailment analysis tool, assess the relationship between the given sentences and classify it as 'entailment' or 'not_entailment'.", | |
| "atk_acc": 71.83, | |
| "atk_prompt": "In your role as an entailment analysis tool, assess the relationship between the given punishments and categorize it as 'entailment' or 'not_entailment'. ", | |
| "transfer_ori_acc": 23.943661971830984, | |
| "transfer_atk_acc": 19.718309859154928 | |
| }, | |
| { | |
| "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": "Belоw are multipl-echoice quеstion concening {}. Indicate 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": 52.48, | |
| "atk_prompt": "Considering your familiarity with {}, attend to the following mutliple-choice matter by picking 'A', 'B', 'C', or 'D'.", | |
| "transfer_ori_acc": 8.156028368794328, | |
| "transfer_atk_acc": 7.801418439716312 | |
| } | |
| ] |