Spaces:
Runtime error
Runtime error
| [ | |
| { | |
| "dataset": "cola", | |
| "type": "task", | |
| "origin_acc": 80.5, | |
| "origin_prompt": "Analyze the provided sentence and classify its grammatical correctness as 'Acceptable' or 'Unacceptable'.", | |
| "atk_acc": 67.5, | |
| "atk_prompt": "Analysing the provided sentences and classify its pronouns correct as 'Acceptable' or 'Unacceptable'. ", | |
| "transfer_ori_acc": 86.0, | |
| "transfer_atk_acc": 84.0 | |
| }, | |
| { | |
| "dataset": "cola", | |
| "type": "role", | |
| "origin_acc": 81.0, | |
| "origin_prompt": "In the role of a syntax analyzer, examine the grammar of the provided sentence and decide if it is correct, answering with 'acceptable' for grammatically correct sentences or 'unacceptable' for incorrect ones.", | |
| "atk_acc": 77.5, | |
| "atk_prompt": "In the role of a syntax checker, examine the grammɑr of the provided sentence and decide if it is correct, answering with 'acceptable' for grammatically correct sentence or 'unacceptable' for incorrect ones. ", | |
| "transfer_ori_acc": 86.5, | |
| "transfer_atk_acc": 86.8 | |
| }, | |
| { | |
| "dataset": "mrpc", | |
| "type": "task", | |
| "origin_acc": 73.0, | |
| "origin_prompt": "Assess if the two given sentences have equivalent meanings by selecting 'equivalent' or 'not_equivalent'.", | |
| "atk_acc": 68.0, | |
| "atk_prompt": "Ass ess if the two gien sentences have equivalent meanings by selecting 'equivalent' or 'not_equivalent'. ", | |
| "transfer_ori_acc": 84.06862745098039, | |
| "transfer_atk_acc": 84.06862745098039 | |
| }, | |
| { | |
| "dataset": "mrpc", | |
| "type": "role", | |
| "origin_acc": 71.5, | |
| "origin_prompt": "As a linguistic comparator, review the following pair of sentences and determine their semantic equivalence by choosing 'equivalent' or 'not_equivalent'.", | |
| "atk_acc": 64.5, | |
| "atk_prompt": "As a linguistic comparator, review the following torque of sentences and determine their semantiϲ eԛuivalence by choosing 'equivalent' or 'not_equivalent'. ", | |
| "transfer_ori_acc": 85.5392156862745, | |
| "transfer_atk_acc": 86.27450980392157 | |
| }, | |
| { | |
| "dataset": "qnli", | |
| "type": "task", | |
| "origin_acc": 85.0, | |
| "origin_prompt": "Examine the context and question, and determine if the context logically implies the answer by selecting 'entailment' or 'not_entailment'.", | |
| "atk_acc": 76.0, | |
| "atk_prompt": "Examine the cntext and question, and determine if the backdrop logically implies the answer by selecting 'entailment' or 'not_entailment'. ", | |
| "transfer_ori_acc": 93.5, | |
| "transfer_atk_acc": 93.60000000000001 | |
| }, | |
| { | |
| "dataset": "qnli", | |
| "type": "role", | |
| "origin_acc": 83.0, | |
| "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": 73.5, | |
| "atk_prompt": "Aѕ a semantic researcher, evaluate si the gave framework supports the respond to the question and choose 'entailment' or 'not_entailment'. ", | |
| "transfer_ori_acc": 94.0, | |
| "transfer_atk_acc": 93.7 | |
| }, | |
| { | |
| "dataset": "qqp", | |
| "type": "task", | |
| "origin_acc": 82.5, | |
| "origin_prompt": "Can these two statements be considered equal in meaning? Answer with 'equivalent' or 'not_equivalent'.", | |
| "atk_acc": 80.0, | |
| "atk_prompt": "Can these two st atements be considered equal in meaning? Ansԝer with 'equivalent' or 'not_equivalent'. ", | |
| "transfer_ori_acc": 87.6, | |
| "transfer_atk_acc": 88.5 | |
| }, | |
| { | |
| "dataset": "qqp", | |
| "type": "role", | |
| "origin_acc": 82.5, | |
| "origin_prompt": "In the capacity of a question assessment system, indicate if the meaning of the provided questions is the same, responding with 'equivalent' or 'not_equivalent'.", | |
| "atk_acc": 80.5, | |
| "atk_prompt": "In the abilities of a question ɑssessment system, indicate if the meaning of the provided matters is the same, responding with 'equivalent' or 'not_equivalent'. ", | |
| "transfer_ori_acc": 88.7, | |
| "transfer_atk_acc": 88.6 | |
| }, | |
| { | |
| "dataset": "rte", | |
| "type": "task", | |
| "origin_acc": 84.0, | |
| "origin_prompt": "Review the two statements and categorize their relationship as either 'entailment' or 'not_entailment'.", | |
| "atk_acc": 76.5, | |
| "atk_prompt": "Review the two declarations and categorize their relationship as neither 'entailment' or 'not_entailment'. ", | |
| "transfer_ori_acc": 92.7797833935018, | |
| "transfer_atk_acc": 92.7797833935018 | |
| }, | |
| { | |
| "dataset": "rte", | |
| "type": "role", | |
| "origin_acc": 83.5, | |
| "origin_prompt": "As an entailment identification system, examine the connection between the following sentences and respond with 'entailment' or 'not_entailment'.", | |
| "atk_acc": 80.0, | |
| "atk_prompt": "As an entailment identification system, eamine the connection between the following sentences and reѕpond with 'entailment' or 'not_entailment'. ", | |
| "transfer_ori_acc": 92.7797833935018, | |
| "transfer_atk_acc": 92.7797833935018 | |
| }, | |
| { | |
| "dataset": "sst2", | |
| "type": "task", | |
| "origin_acc": 95.5, | |
| "origin_prompt": "After examining the following expression, label its emotion as either 'positive' or 'negative'.", | |
| "atk_acc": 74.0, | |
| "atk_prompt": "Ater examining the following expression, etiquette its emotion as nor 'positive' or 'negative'. ", | |
| "transfer_ori_acc": 92.77522935779817, | |
| "transfer_atk_acc": 95.52752293577981 | |
| }, | |
| { | |
| "dataset": "sst2", | |
| "type": "role", | |
| "origin_acc": 97.5, | |
| "origin_prompt": "In the capacity of a sentiment classifier, decide whether the given quote is 'positive' or 'negative'.", | |
| "atk_acc": 93.5, | |
| "atk_prompt": "Onto the capacity of a feeling classifeir, decide si the given quote is 'positive' or 'negative'. ", | |
| "transfer_ori_acc": 96.44495412844036, | |
| "transfer_atk_acc": 96.21559633027523 | |
| }, | |
| { | |
| "dataset": "wnli", | |
| "type": "task", | |
| "origin_acc": 69.01, | |
| "origin_prompt": "Indicate if the connection between the following sentences is 'entailment' or 'not_entailment'.", | |
| "atk_acc": 61.97, | |
| "atk_prompt": "Indicate if the connection between the following sentences is 'entailment' or 'not_entailment' Vq3aBzuZcD. ", | |
| "transfer_ori_acc": 76.05633802816901, | |
| "transfer_atk_acc": 76.05633802816901 | |
| }, | |
| { | |
| "dataset": "wnli", | |
| "type": "role", | |
| "origin_acc": 66.2, | |
| "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": 59.15, | |
| "atk_prompt": "In your role as an entailment analysis tool, assess the relationship between the given sentences and classify it as 'entailment' or 'not_entailment' is77sOXAu8. ", | |
| "transfer_ori_acc": 77.46478873239437, | |
| "transfer_atk_acc": 76.05633802816901 | |
| }, | |
| { | |
| "dataset": "mmlu", | |
| "type": "task", | |
| "origin_acc": 67.5, | |
| "origin_prompt": "In relation to the multiple-choice question on {}, please provide the accurate answer by choosing 'A', 'B', 'C', or 'D'.", | |
| "atk_acc": 61.5, | |
| "atk_prompt": "At relationship to the mul𝚝iple-choice question on {}, please proviԁe the accurate responding by choosing 'A', 'B', 'C', or 'D'. ", | |
| "transfer_ori_acc": 53.54609929078015, | |
| "transfer_atk_acc": 53.54609929078015 | |
| }, | |
| { | |
| "dataset": "mmlu", | |
| "type": "role", | |
| "origin_acc": 65.5, | |
| "origin_prompt": "As someone well-versed in {}, please address the multiple-choice question below by selecting 'A', 'B', 'C', or 'D'.", | |
| "atk_acc": 61.5, | |
| "atk_prompt": "As someone well-vesred in {}, please address the muⅼtiple-choice questioո below by selecting 'A', 'B', 'C', or 'D'.", | |
| "transfer_ori_acc": 53.01418439716312, | |
| "transfer_atk_acc": 53.01418439716312 | |
| }, | |
| { | |
| "dataset": "squad_v2", | |
| "type": "task", | |
| "origin_acc": 72.75, | |
| "origin_prompt": "Based on the given context, provide the best possible answer. If there's no answer available in the context, reply with 'unanswerable'.", | |
| "atk_acc": 67.93, | |
| "atk_prompt": "Based on the giveո context, provide the best pоssible answer. If there's no answer available in the contex𝚝, reply with 'unanswerable'.", | |
| "transfer_ori_acc": 90.04896616541353, | |
| "transfer_atk_acc": 90.04896616541353 | |
| }, | |
| { | |
| "dataset": "squad_v2", | |
| "type": "role", | |
| "origin_acc": 70.63, | |
| "origin_prompt": "As a proficient expert in the given context, search for the most relevant answer. If the answer cannot be found, respond by saying 'unanswerable'.", | |
| "atk_acc": 68.31, | |
| "atk_prompt": "As a profcient expert in the given cоntext, search for the most relevant answer. If the anwser cannot be unearthed, respond by saying 'unanswerable'.", | |
| "transfer_ori_acc": 90.54896616541353, | |
| "transfer_atk_acc": 90.54896616541353 | |
| }, | |
| { | |
| "dataset": "iwslt", | |
| "type": "task", | |
| "origin_acc": 0.23, | |
| "origin_prompt": "Please perform a translation of the given sentence, converting it from {} to {}.", | |
| "atk_acc": 0.23, | |
| "atk_prompt": "Pⅼease perform a translating of the givеn sentence, conversion it from {} to {}. ", | |
| "transfer_ori_acc": 0.23770260910322083, | |
| "transfer_atk_acc": 0.2378477137621768 | |
| }, | |
| { | |
| "dataset": "iwslt", | |
| "type": "role", | |
| "origin_acc": 0.24, | |
| "origin_prompt": "Assuming the responsibilities of a professional translator, translate the subsequent text passage from {} to {}.", | |
| "atk_acc": 0.23, | |
| "atk_prompt": "Assuminɡ the responsibilities of a professional transla𝚝or, translate the subsequent text passage from {} to {}. ", | |
| "transfer_ori_acc": 0.2676477143562027, | |
| "transfer_atk_acc": 0.26838348206750196 | |
| }, | |
| { | |
| "dataset": "un_multi", | |
| "type": "task", | |
| "origin_acc": 0.35, | |
| "origin_prompt": "Please perform a translation of the given sentence, converting it from {} to {}.", | |
| "atk_acc": 0.35, | |
| "atk_prompt": "Plеase perform a translation of the given sentence, convert it from {} to {}. ", | |
| "transfer_ori_acc": 0.35614481480027904, | |
| "transfer_atk_acc": 0.3540588157620361 | |
| }, | |
| { | |
| "dataset": "un_multi", | |
| "type": "role", | |
| "origin_acc": 0.35, | |
| "origin_prompt": "As a qualified translator, convert the given sentence from its original {} language to the target language {}.", | |
| "atk_acc": 0.34, | |
| "atk_prompt": "As a eligible translator, convert the given sentence from its orіginal {} language to the tarɡet language {}. ", | |
| "transfer_ori_acc": 0.35395992027011125, | |
| "transfer_atk_acc": 0.35407154067545005 | |
| }, | |
| { | |
| "dataset": "math", | |
| "type": "task", | |
| "origin_acc": 23.12, | |
| "origin_prompt": "Calculate the answer to the following math query about {}.", | |
| "atk_acc": 20.62, | |
| "atk_prompt": "Calculate the answer to the 𝚏ollowing math query about {}. ", | |
| "transfer_ori_acc": 16.25, | |
| "transfer_atk_acc": 16.25 | |
| }, | |
| { | |
| "dataset": "math", | |
| "type": "role", | |
| "origin_acc": 22.5, | |
| "origin_prompt": "As a mathematics instructor, calculate the answer to the following problem related to {}.", | |
| "atk_acc": 19.38, | |
| "atk_prompt": "Since a mathematics istructor, calculate the answer to the following problem related to {}. ", | |
| "transfer_ori_acc": 15.625, | |
| "transfer_atk_acc": 15.0 | |
| } | |
| ] |