Spaces:
Runtime error
Runtime error
| [ | |
| { | |
| "dataset": "cola", | |
| "type": "task", | |
| "origin_acc": 86.2, | |
| "origin_prompt": "Assess the following sentence and determine if it is grammatically correct. Respond with 'Acceptable' or 'Unacceptable':", | |
| "atk_acc": 78.7, | |
| "atk_prompt": "Assess the following sentence and identify if it is pronouns cоrrect. Replying with 'Acceptable' or 'Unacceptable':", | |
| "transfer_ori_acc": 76.5, | |
| "transfer_atk_acc": 76.5 | |
| }, | |
| { | |
| "dataset": "cola", | |
| "type": "role", | |
| "origin_acc": 86.0, | |
| "origin_prompt": "As a grammar identification system, examine the provided sentence and respond with 'acceptable' for grammatically correct sentences or 'unacceptable' for incorrect ones:", | |
| "atk_acc": 81.0, | |
| "atk_prompt": "Aѕ a grammar identificatiоn systems, examine the provided sentence and respoոd with 'acceptable' for pronouns rightness sentence or 'unacceptable' for incorrect those:", | |
| "transfer_ori_acc": 78.0, | |
| "transfer_atk_acc": 77.0 | |
| }, | |
| { | |
| "dataset": "mrpc", | |
| "type": "task", | |
| "origin_acc": 86.76, | |
| "origin_prompt": "Please analyze the provided sentences and indicate if their meanings are the same by choosing 'equivalent' or 'not_equivalent'.", | |
| "atk_acc": 83.09, | |
| "atk_prompt": "Invited analyze the provideԁ verdicts and indicate if their meanings are the same by selecting 'equivalent' or 'not_equivalent'. ", | |
| "transfer_ori_acc": 76.5, | |
| "transfer_atk_acc": 74.5 | |
| }, | |
| { | |
| "dataset": "mrpc", | |
| "type": "role", | |
| "origin_acc": 87.99, | |
| "origin_prompt": "In your capacity as a language analyst, assess the following sentences and classify their similarity as 'equivalent' or 'not_equivalent'.", | |
| "atk_acc": 81.13, | |
| "atk_prompt": "In your capacity as a linguistics aոalyst, evaluate the following sentences and classify their metaphor as 'equivalent' or 'not_equivalent'. ", | |
| "transfer_ori_acc": 72.5, | |
| "transfer_atk_acc": 14.499999999999998 | |
| }, | |
| { | |
| "dataset": "qnli", | |
| "type": "task", | |
| "origin_acc": 94.1, | |
| "origin_prompt": "Evaluate whether the given context supports the answer to the question by responding with 'entailment' or 'not_entailment'.", | |
| "atk_acc": 93.3, | |
| "atk_prompt": "Evaluate whetheⲅ the given context favours the answer to the question by responding with 'entailment' or 'not_entailment'. ", | |
| "transfer_ori_acc": 79.0, | |
| "transfer_atk_acc": 77.0 | |
| }, | |
| { | |
| "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": 93.1, | |
| "atk_prompt": "In your role as a linguistic searchers, ԁetermine if the context awarded presupposes the answer to the questions and provide your conclusions with 'entailment' or 'not_entailment'. ", | |
| "transfer_ori_acc": 70.5, | |
| "transfer_atk_acc": 73.5 | |
| }, | |
| { | |
| "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": 86.4, | |
| "atk_prompt": "Do these two verdicts convey the same connotation? Denotes with 'equivalent' or 'not_equivalent'. ", | |
| "transfer_ori_acc": 79.5, | |
| "transfer_atk_acc": 76.0 | |
| }, | |
| { | |
| "dataset": "qqp", | |
| "type": "role", | |
| "origin_acc": 88.5, | |
| "origin_prompt": "As a tool for determining question equivalence, review the questions and categorize their similarity as either 'equivalent' or 'not_equivalent'.", | |
| "atk_acc": 78.2, | |
| "atk_prompt": "As a tool for deciding question equivalence, review the problems and categorize their metaphor as neither 'equivalent' or 'not_equivalent'. ", | |
| "transfer_ori_acc": 82.0, | |
| "transfer_atk_acc": 46.5 | |
| }, | |
| { | |
| "dataset": "rte", | |
| "type": "task", | |
| "origin_acc": 94.22, | |
| "origin_prompt": "Are the following two sentences entailment or not_entailment? Answer me with \"entailment\" or \"not_entailment\", just one word.", | |
| "atk_acc": 89.89, | |
| "atk_prompt": "Are the subsequent secondly sentencing entailment or not_entailment? Answer me with \"entailment\" or \"not_entailment\", just one word. ", | |
| "transfer_ori_acc": 80.5, | |
| "transfer_atk_acc": 78.0 | |
| }, | |
| { | |
| "dataset": "rte", | |
| "type": "role", | |
| "origin_acc": 93.86, | |
| "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": 90.25, | |
| "atk_prompt": "Throughout your role as an entailment analysis instrument, assess the relationship between the given punishments and classify it as 'entailment' or 'not_entailment':", | |
| "transfer_ori_acc": 78.0, | |
| "transfer_atk_acc": 67.0 | |
| }, | |
| { | |
| "dataset": "sst2", | |
| "type": "task", | |
| "origin_acc": 96.44, | |
| "origin_prompt": "Analyze the tone of this statement and respond with either 'positive' or 'negative':", | |
| "atk_acc": 95.76, | |
| "atk_prompt": "Analysis the tone of this speeches and respond with or 'positive' or 'negative': ", | |
| "transfer_ori_acc": 89.5, | |
| "transfer_atk_acc": 88.5 | |
| }, | |
| { | |
| "dataset": "sst2", | |
| "type": "role", | |
| "origin_acc": 96.33, | |
| "origin_prompt": "As a sentiment classifier, determine whether the following text is 'positive' or 'negative'. Please classify:", | |
| "atk_acc": 93.92, | |
| "atk_prompt": "Aѕ a emotion classifier, determine whether the follow ing text is 'positive' or 'negative'. Inviting classify: ", | |
| "transfer_ori_acc": 90.5, | |
| "transfer_atk_acc": 88.0 | |
| }, | |
| { | |
| "dataset": "wnli", | |
| "type": "task", | |
| "origin_acc": 78.87, | |
| "origin_prompt": "Are the following two sentences entailment or not_entailment? Answer me with \"entailment\" or \"not_entailment\", just one word.", | |
| "atk_acc": 74.65, | |
| "atk_prompt": "Are the flolowing two sentences entailment or not_entailment? Answer me with \"entailment\" or \"not_entailment\", just one adjective. ", | |
| "transfer_ori_acc": 64.7887323943662, | |
| "transfer_atk_acc": 64.7887323943662 | |
| }, | |
| { | |
| "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": "Functioոing as an entailment evaluation tool, analyze the provided sentences and decіde if their rapport is 'entailment' or 'not_entailment':", | |
| "transfer_ori_acc": 50.70422535211267, | |
| "transfer_atk_acc": 53.52112676056338 | |
| }, | |
| { | |
| "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": 51.24, | |
| "atk_prompt": "In the multiple-choice question rel ated to {}, inviting choose the most accurate answer from 'A', 'B', 'C', or 'D'. ", | |
| "transfer_ori_acc": 63.5, | |
| "transfer_atk_acc": 60.5 | |
| }, | |
| { | |
| "dataset": "mmlu", | |
| "type": "role", | |
| "origin_acc": 53.19, | |
| "origin_prompt": "As a knowledgeable individual in {}, provide your response to the multiple-choice question by choosing 'A', 'B', 'C', or 'D'.", | |
| "atk_acc": 51.24, | |
| "atk_prompt": "As a knowledgeable indiivdual in {}, provide your replies to the multiple-choice problem by choosing 'A', 'B', 'C', or 'D'.", | |
| "transfer_ori_acc": 60.0, | |
| "transfer_atk_acc": 62.0 | |
| }, | |
| { | |
| "dataset": "squad_v2", | |
| "type": "task", | |
| "origin_acc": 89.88, | |
| "origin_prompt": "Please derive the most fitting answer from the context. If there isn't an answer in the context, respond with 'unanswerable'.", | |
| "atk_acc": 88.88, | |
| "atk_prompt": "Please ԁerive the most fitting answer from the coոtext. If there isn't an answer in the context, respond with 'unanswerable'.", | |
| "transfer_ori_acc": 68.73966126471147, | |
| "transfer_atk_acc": 68.32769616246503 | |
| }, | |
| { | |
| "dataset": "squad_v2", | |
| "type": "role", | |
| "origin_acc": 90.05, | |
| "origin_prompt": "As a well-informed specialist familiar with the context, provide an answer to the question. If the context doesn't contain an answer, reply with 'unanswerable'.", | |
| "atk_acc": 88.15, | |
| "atk_prompt": "As a well-ifnormed specialist familiar with the context, provide an answers to the question. If the context doesn't contain an replying, reply with 'unanswerable'.", | |
| "transfer_ori_acc": 57.51551811147121, | |
| "transfer_atk_acc": 56.18298772762505 | |
| }, | |
| { | |
| "dataset": "iwslt", | |
| "type": "task", | |
| "origin_acc": 0.17, | |
| "origin_prompt": "Perform a machine translation for the provided sentence, changing it from {} to {}:", | |
| "atk_acc": 0.16, | |
| "atk_prompt": "Perform a mɑchine translation for the provided sentеnce, changing it from {} to {}:", | |
| "transfer_ori_acc": 0.2213426176232537, | |
| "transfer_atk_acc": 0.2221768844134593 | |
| }, | |
| { | |
| "dataset": "iwslt", | |
| "type": "role", | |
| "origin_acc": 0.18, | |
| "origin_prompt": "Assuming the role of an expert language translator, translate the given text from {} to {}:", | |
| "atk_acc": 0.15, | |
| "atk_prompt": "Assuming the role of an expert language tranѕlator, translate the given tеxt from {} to {}: ", | |
| "transfer_ori_acc": 0.22228614624164078, | |
| "transfer_atk_acc": 0.22384198460349325 | |
| }, | |
| { | |
| "dataset": "un_multi", | |
| "type": "task", | |
| "origin_acc": 0.32, | |
| "origin_prompt": "Please perform a translation of the given sentence, converting it from {} to {}:", | |
| "atk_acc": 0.31, | |
| "atk_prompt": "Please perform a translation of the given sentence, conevrting it from {} to {}:", | |
| "transfer_ori_acc": 0.3309447106416932, | |
| "transfer_atk_acc": 0.3365823327588491 | |
| }, | |
| { | |
| "dataset": "un_multi", | |
| "type": "role", | |
| "origin_acc": 0.32, | |
| "origin_prompt": "Assuming the responsibilities of a professional translator, translate the subsequent text passage from {} to {}:", | |
| "atk_acc": 0.24, | |
| "atk_prompt": "Assuming the responsibilities of a professional tⲅanslator, translate the subseԛuent text рassage from {} to {}: ", | |
| "transfer_ori_acc": 0.3345450951028871, | |
| "transfer_atk_acc": 0.335831807535562 | |
| }, | |
| { | |
| "dataset": "math", | |
| "type": "task", | |
| "origin_acc": 15.0, | |
| "origin_prompt": "Compute the result of this math task concerning {}:", | |
| "atk_acc": 11.25, | |
| "atk_prompt": "Compute the reѕult of this math task relative {}:", | |
| "transfer_ori_acc": 6.875000000000001, | |
| "transfer_atk_acc": 6.25 | |
| }, | |
| { | |
| "dataset": "math", | |
| "type": "role", | |
| "origin_acc": 15.0, | |
| "origin_prompt": "As a mathematics instructor, calculate the answer to the following problem related to {}:", | |
| "atk_acc": 9.38, | |
| "atk_prompt": "Since a calculus instructor, calculate the responding to the following problem related to {}: ", | |
| "transfer_ori_acc": 5.0, | |
| "transfer_atk_acc": 4.375 | |
| } | |
| ] |