[ { "dataset": "cola", "type": "task", "origin_acc": 80.5, "origin_prompt": "Examine the given sentence and decide if it is grammatically sound. Answer with either 'Acceptable' or 'Unacceptable'.", "atk_acc": 79.5, "atk_prompt": "Examine the given sentence and decide if it is grammatically sound. Answer with either 'Acceptable' or 'Unacceptable' and true is true and true is true and true is true and true is true and true is true . ", "transfer_ori_acc": 0.8999999999999999, "transfer_atk_acc": 0.4 }, { "dataset": "cola", "type": "role", "origin_acc": 81.5, "origin_prompt": "Functioning as a grammar evaluation tool, analyze the given sentence and decide if it is grammatically correct, responding with 'acceptable' or 'unacceptable'.", "atk_acc": 80.5, "atk_prompt": "Functioning as a grammar evaluation tool, analyze the given sentence and decide if it is grammatically correct, responding with 'acceptable' or 'unacceptable' and false is not true . ", "transfer_ori_acc": 23.9, "transfer_atk_acc": 9.4 }, { "dataset": "mrpc", "type": "task", "origin_acc": 73.5, "origin_prompt": "Assess if the two given sentences have equivalent meanings by selecting 'equivalent' or 'not_equivalent'.", "atk_acc": 71.5, "atk_prompt": "Assess if the two given sentences have equivalent meanings by selecting 'equivalent' or 'not_equivalent' and true is true and true is true and true is true and true is true and true is true . ", "transfer_ori_acc": 69.36274509803921, "transfer_atk_acc": 69.11764705882352 }, { "dataset": "mrpc", "type": "role", "origin_acc": 72.5, "origin_prompt": "In the role of a textual comparison specialist, examine the given sentences and decide if they share the same meaning, responding with 'equivalent' or 'not_equivalent'.", "atk_acc": 70.0, "atk_prompt": "In the role of a textual comparison specialist, examine the given sentences and decide if they share the same meaning, responding with 'equivalent' or 'not_equivalent' and true is true . ", "transfer_ori_acc": 69.36274509803921, "transfer_atk_acc": 63.48039215686274 }, { "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": 79.5, "atk_prompt": "Examine the context and question, and determine if the context logically implies the answer by selecting 'entailment' or 'not_entailment' and true is true and true is true and true is true and true is true and true is true . ", "transfer_ori_acc": 26.900000000000002, "transfer_atk_acc": 11.3 }, { "dataset": "qnli", "type": "role", "origin_acc": 84.0, "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": 81.5, "atk_prompt": "As a semantic researcher, evaluate whether the provided context supports the answer to the question and choose 'entailment' or 'not_entailment' and false is not true . ", "transfer_ori_acc": 41.6, "transfer_atk_acc": 31.7 }, { "dataset": "qqp", "type": "task", "origin_acc": 81.5, "origin_prompt": "Can these two statements be considered equal in meaning? Answer with 'equivalent' or 'not_equivalent'.", "atk_acc": 81.0, "atk_prompt": "Can these two statements be considered equal in meaning? Answer with 'equivalent' or 'not_equivalent' and false is not true . ", "transfer_ori_acc": 36.3, "transfer_atk_acc": 41.699999999999996 }, { "dataset": "qqp", "type": "role", "origin_acc": 83.0, "origin_prompt": "As an instrument for question comparison evaluation, consider the questions and determine if their meaning is the same, responding with 'equivalent' for similar questions or 'not_equivalent' for different questions.", "atk_acc": 82.0, "atk_prompt": "As an instrument for question comparison evaluation, consider the questions and determine if their meaning is the same, responding with 'equivalent' for similar questions or 'not_equivalent' for different questions and true is true and true is true and true is true and true is true and true is true . ", "transfer_ori_acc": 35.3, "transfer_atk_acc": 40.2 }, { "dataset": "rte", "type": "task", "origin_acc": 85.0, "origin_prompt": "Does the relationship between the given sentences represent entailment or not_entailment? Respond with 'entailment' or 'not_entailment'.", "atk_acc": 82.0, "atk_prompt": "Does the relationship between the given sentences represent entailment or not_entailment? Respond with 'entailment' or 'not_entailment' and false is not true . ", "transfer_ori_acc": 46.20938628158845, "transfer_atk_acc": 48.014440433213 }, { "dataset": "rte", "type": "role", "origin_acc": 83.0, "origin_prompt": "As an entailment identification system, examine the connection between the following sentences and respond with 'entailment' or 'not_entailment'.", "atk_acc": 83.0, "atk_prompt": "As an entailment identification system, examine the connection between the following sentences and respond with 'entailment' or 'not_entailment' and false is not true . ", "transfer_ori_acc": 46.20938628158845, "transfer_atk_acc": 41.15523465703971 }, { "dataset": "sst2", "type": "task", "origin_acc": 97.0, "origin_prompt": "Evaluate the sentiment of the given text and classify it as 'positive' or 'negative'.", "atk_acc": 95.5, "atk_prompt": "Evaluate the sentiment of the given text and classify it as 'positive' or 'negative' and true is true . ", "transfer_ori_acc": 10.435779816513762, "transfer_atk_acc": 1.94954128440367 }, { "dataset": "sst2", "type": "role", "origin_acc": 97.0, "origin_prompt": "As a sentiment classifier, determine whether the following text is 'positive' or 'negative'.", "atk_acc": 96.0, "atk_prompt": "As a sentiment classifier, determine whether the following text is 'positive' or 'negative' and false is not true . ", "transfer_ori_acc": 15.36697247706422, "transfer_atk_acc": 8.486238532110093 }, { "dataset": "wnli", "type": "task", "origin_acc": 67.61, "origin_prompt": "Indicate if the connection between the following sentences is 'entailment' or 'not_entailment'.", "atk_acc": 60.56, "atk_prompt": "Indicate if the connection between the later sentences is 'entailment' or 'not_entailment'. ", "transfer_ori_acc": 9.859154929577464, "transfer_atk_acc": 9.859154929577464 }, { "dataset": "wnli", "type": "role", "origin_acc": 66.2, "origin_prompt": "In the role of a semantic relationship analyzer, examine the connection between the given sentences and decide if they exhibit entailment or not_entailment. Answer with 'entailment' or 'not_entailment'.", "atk_acc": 59.15, "atk_prompt": "In the role of a semantic relationship analyzer, investigated the linking between the given sentences and decide if they exhibit entailment or not_entailment. Answer with 'entailment' or 'not_entailment'. ", "transfer_ori_acc": 5.633802816901409, "transfer_atk_acc": 12.676056338028168 }, { "dataset": "mmlu", "type": "task", "origin_acc": 66.5, "origin_prompt": "Please respond to the multiple-choice question about {} by selecting the appropriate answer: 'A', 'B', 'C', or 'D'.", "atk_acc": 61.5, "atk_prompt": "Please respond to the multiple-choice question about {} by selecting the appropriate answer: 'A', 'B', 'C', or 'D' and false is not true . ", "transfer_ori_acc": 8.865248226950355, "transfer_atk_acc": 11.52482269503546 }, { "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": 59.5, "atk_prompt": "As someone well-versed in {}, please address the multiple-choice question below by selecting 'A', 'B', 'C', or 'D' and false is not true .", "transfer_ori_acc": 8.51063829787234, "transfer_atk_acc": 15.602836879432624 } ]