Spaces:
Runtime error
Runtime error
| [ | |
| { | |
| "dataset": "cola", | |
| "type": "task", | |
| "origin_acc": 86.0, | |
| "origin_prompt": "Examine the given sentence and decide if it is grammatically sound. Answer with either 'Acceptable' or 'Unacceptable':", | |
| "atk_acc": 25.3, | |
| "atk_prompt": "find the particular sentence and look if it is grammaticaldefinitely present. responded with neither 'Acceptable' or 'Unacceptable':", | |
| "transfer_ori_acc": 76.5, | |
| "transfer_atk_acc": 78.5 | |
| }, | |
| { | |
| "dataset": "cola", | |
| "type": "role", | |
| "origin_acc": 86.1, | |
| "origin_prompt": "In your role as a grammar check tool, assess the following sentence and classify it as 'acceptable' if it is grammatically correct or 'unacceptable' if it is incorrect:", | |
| "atk_acc": 30.9, | |
| "atk_prompt": "should your job as a grammar get check, assess the following sentence and classify it as 'acceptable' if it is grammaticalmore improper or 'unacceptable' if it is contradictory:", | |
| "transfer_ori_acc": 78.0, | |
| "transfer_atk_acc": 78.5 | |
| }, | |
| { | |
| "dataset": "mrpc", | |
| "type": "task", | |
| "origin_acc": 88.24, | |
| "origin_prompt": "In your capacity as a language analyst, assess the following sentences and classify their similarity as 'equivalent' or 'not_equivalent'.", | |
| "atk_acc": 70.1, | |
| "atk_prompt": "during your capacity as a grammatical analytic, calculate the following words and classify their difference as 'equivalent' or 'not_equivalent'. ", | |
| "transfer_ori_acc": 72.0, | |
| "transfer_atk_acc": 13.5 | |
| }, | |
| { | |
| "dataset": "mrpc", | |
| "type": "role", | |
| "origin_acc": 87.25, | |
| "origin_prompt": "Can the given sentences be considered semantically identical? Please reply with 'equivalent' or 'not_equivalent'.", | |
| "atk_acc": 34.8, | |
| "atk_prompt": "can the following sentences be considered semanticmore inferior? this reply with 'equivalent' or 'not_equivalent'. ", | |
| "transfer_ori_acc": 75.5, | |
| "transfer_atk_acc": 74.5 | |
| }, | |
| { | |
| "dataset": "qnli", | |
| "type": "task", | |
| "origin_acc": 94.1, | |
| "origin_prompt": "Based on the information in the context, decide if the answer to the question is justified by choosing 'entailment' or 'not_entailment'.", | |
| "atk_acc": 52.7, | |
| "atk_prompt": "Based on the info in the context, decide if the object to the question is wrong by choosing 'entailment' or 'not_entailment'. ", | |
| "transfer_ori_acc": 75.5, | |
| "transfer_atk_acc": 35.0 | |
| }, | |
| { | |
| "dataset": "qnli", | |
| "type": "role", | |
| "origin_acc": 94.2, | |
| "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": 42.6, | |
| "atk_prompt": "while a semantic researcher, evaluate positive the supported context returns the answer to the question and reject 'entailment' or 'not_entailment'. ", | |
| "transfer_ori_acc": 76.0, | |
| "transfer_atk_acc": 46.5 | |
| }, | |
| { | |
| "dataset": "qqp", | |
| "type": "task", | |
| "origin_acc": 88.2, | |
| "origin_prompt": "Please indicate if the following pair of sentences share the same meaning by responding with 'equivalent' or 'not_equivalent'.", | |
| "atk_acc": 70.8, | |
| "atk_prompt": "Please indicate if the following individual of verbs share the same meaning by auxiliary with 'equivalent' or 'not_equivalent'. ", | |
| "transfer_ori_acc": 81.5, | |
| "transfer_atk_acc": 77.5 | |
| }, | |
| { | |
| "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": 70.9, | |
| "atk_prompt": "As a tool for weighing question equivalence, review the data and codeegoassociate their difference as neither 'equivalent' or 'not_equivalent'. ", | |
| "transfer_ori_acc": 81.5, | |
| "transfer_atk_acc": 78.0 | |
| }, | |
| { | |
| "dataset": "rte", | |
| "type": "task", | |
| "origin_acc": 94.22, | |
| "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": 88.45, | |
| "atk_prompt": "examine the parent of sentences and explain if they exhibit entailment or not_entailment. consider with neither 'entailment' or 'not_entailment'.", | |
| "transfer_ori_acc": 81.0, | |
| "transfer_atk_acc": 52.5 | |
| }, | |
| { | |
| "dataset": "rte", | |
| "type": "role", | |
| "origin_acc": 93.86, | |
| "origin_prompt": "Acting as an entailment detection instrument, determine if the given pair of sentences demonstrates entailment or not_entailment. Answer with 'entailment' or 'not_entailment':", | |
| "atk_acc": 83.03, | |
| "atk_prompt": "Acting as an entailment on instrument, determine if the hit pair of verb appears entailment or not_entailment. answers with 'entailment' or 'not_entailment':", | |
| "transfer_ori_acc": 83.5, | |
| "transfer_atk_acc": 69.5 | |
| }, | |
| { | |
| "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": 0.11, | |
| "atk_prompt": "Analyze the topic of this phrase and responding with neither 'positive' or 'negative': ", | |
| "transfer_ori_acc": 89.5, | |
| "transfer_atk_acc": 0.0 | |
| }, | |
| { | |
| "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": 43.69, | |
| "atk_prompt": "like a sentiment classifier, identify neither the following text is 'positive' or 'negative'. from submit: ", | |
| "transfer_ori_acc": 90.5, | |
| "transfer_atk_acc": 37.0 | |
| }, | |
| { | |
| "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": 71.83, | |
| "atk_prompt": "Are the main two sentences entailment or not_entailment? begin me with \"entailment\" or \"not_entailment\", just the word. ", | |
| "transfer_ori_acc": 64.7887323943662, | |
| "transfer_atk_acc": 57.74647887323944 | |
| }, | |
| { | |
| "dataset": "wnli", | |
| "type": "role", | |
| "origin_acc": 78.87, | |
| "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": 70.42, | |
| "atk_prompt": "In your role as an entailment analysis tool, report the commitment between the and are and classify it as 'entailment' or 'not_entailment':", | |
| "transfer_ori_acc": 52.112676056338024, | |
| "transfer_atk_acc": 52.112676056338024 | |
| }, | |
| { | |
| "dataset": "mmlu", | |
| "type": "task", | |
| "origin_acc": 52.84, | |
| "origin_prompt": "Please respond to the multiple-choice question about {} by selecting the appropriate answer: 'A', 'B', 'C', or 'D'.", | |
| "atk_acc": 17.38, | |
| "atk_prompt": "not respond to the multiple-response question about {} by choosing the responses correctly: 'A', 'B', 'C', or 'D'. ", | |
| "transfer_ori_acc": 61.5, | |
| "transfer_atk_acc": 52.0 | |
| }, | |
| { | |
| "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": 37.94, | |
| "atk_prompt": "not a knowledgeable example in {}, state your response to the multiple-is question by choosing 'A', 'B', 'C', or 'D'.", | |
| "transfer_ori_acc": 60.0, | |
| "transfer_atk_acc": 56.99999999999999 | |
| }, | |
| { | |
| "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": 84.86, | |
| "atk_prompt": "wait choose the most fitting number from the context. If there isn't an answer in the context, answer with 'unanswerable'.", | |
| "transfer_ori_acc": 69.08748735166799, | |
| "transfer_atk_acc": 76.95185295253945 | |
| }, | |
| { | |
| "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": 12.09, | |
| "atk_prompt": "a a well-informed answer relevant with the context, provide an question to the question. if the context doesn't contain an inquiry, challenge with 'unanswerable'.", | |
| "transfer_ori_acc": 56.6655181114712, | |
| "transfer_atk_acc": 28.69923950813623 | |
| }, | |
| { | |
| "dataset": "iwslt", | |
| "type": "task", | |
| "origin_acc": 0.17, | |
| "origin_prompt": "Convert the following sentence from its original {} language to the target language {}:", | |
| "atk_acc": 0.16, | |
| "atk_prompt": "Convert the following sentence from its original {} translation to the current language {}:", | |
| "transfer_ori_acc": 0.22260182472721973, | |
| "transfer_atk_acc": 0.2170379591753523 | |
| }, | |
| { | |
| "dataset": "iwslt", | |
| "type": "role", | |
| "origin_acc": 0.18, | |
| "origin_prompt": "Acting as a professional translator, translate the provided sentence from {} to {}:", | |
| "atk_acc": 0.15, | |
| "atk_prompt": "Acting as a professional [UNK], translate the displayed sentence from {} to {}: ", | |
| "transfer_ori_acc": 0.2194769364361696, | |
| "transfer_atk_acc": 0.21620968385981598 | |
| }, | |
| { | |
| "dataset": "un_multi", | |
| "type": "task", | |
| "origin_acc": 0.32, | |
| "origin_prompt": "Translate the provided sentence from {} to {} while maintaining the original meaning and context:", | |
| "atk_acc": 0.3, | |
| "atk_prompt": "Translate the provided sentence from {} to {} while reverse the original flow and context:", | |
| "transfer_ori_acc": 0.32770376671435103, | |
| "transfer_atk_acc": 0.2935218182851911 | |
| }, | |
| { | |
| "dataset": "un_multi", | |
| "type": "role", | |
| "origin_acc": 0.32, | |
| "origin_prompt": "As a language specialist, accurately translate the provided sentence from {} to {}:", | |
| "atk_acc": 0.3, | |
| "atk_prompt": "a a language specialists, just translate the provided sentence from {} to {}: ", | |
| "transfer_ori_acc": 0.3268812389000029, | |
| "transfer_atk_acc": 0.3328840611498249 | |
| }, | |
| { | |
| "dataset": "math", | |
| "type": "task", | |
| "origin_acc": 14.37, | |
| "origin_prompt": "Determine the solution to this mathematical problem related to {}:", | |
| "atk_acc": 2.5, | |
| "atk_prompt": "identify the problem to this mathematical problem related to {}:", | |
| "transfer_ori_acc": 5.625, | |
| "transfer_atk_acc": 0.625 | |
| }, | |
| { | |
| "dataset": "math", | |
| "type": "role", | |
| "origin_acc": 15.0, | |
| "origin_prompt": "In the shoes of a mathematics master, obtain the result for this math question that includes {}:", | |
| "atk_acc": 2.5, | |
| "atk_prompt": "In the shoes of a complexity master, obtain the question for this math question that includes {}: ", | |
| "transfer_ori_acc": 5.625, | |
| "transfer_atk_acc": 0.625 | |
| } | |
| ] |