results_transfer/google-flan-t5-large_chatgpt/deepwordbug_3_shot.json

[
    {
        "dataset": "cola",
        "type": "task",
        "origin_acc": 77.8,
        "origin_prompt": "Is the provided sentence grammatically correct? Respond with 'Acceptable' or 'Unacceptable'.",
        "atk_acc": 68.6,
        "atk_prompt": "Is the provided semtence rammatically corrct? Respond with 'Acceptable' or 'Unacceptable'. ",
        "transfer_ori_acc": 81.0,
        "transfer_atk_acc": 81.0
    },
    {
        "dataset": "cola",
        "type": "role",
        "origin_acc": 75.7,
        "origin_prompt": "While performing grammar analysis, classify the grammar of the following sentence as 'acceptable' for correct grammar or 'unacceptable' for incorrect grammar.",
        "atk_acc": 70.5,
        "atk_prompt": "While hperforming grammNar anlaysis, classfiy the grammar of the foBlowing sentence as 'acceptable' for corrept grammgar or 'unacceptable' for incborrect grMammar. ",
        "transfer_ori_acc": 82.0,
        "transfer_atk_acc": 81.0
    },
    {
        "dataset": "mrpc",
        "type": "task",
        "origin_acc": 83.09,
        "origin_prompt": "Evaluate whether the two provided sentences convey the same meaning by answering 'equivalent' or 'not_equivalent'.",
        "atk_acc": 78.92,
        "atk_prompt": "Evaluate whether the two provided senetnces convey the same meaning by answering 'equivalent' or 'not_equivalent'. ",
        "transfer_ori_acc": 67.0,
        "transfer_atk_acc": 66.0
    },
    {
        "dataset": "mrpc",
        "type": "role",
        "origin_acc": 81.37,
        "origin_prompt": "As a semantic comparison expert, evaluate the given pair of sentences and determine if they are 'equivalent' or 'not_equivalent'.",
        "atk_acc": 76.72,
        "atk_prompt": "As a semantic comparisKon experEt, evaluate the given pari of sentence and determine if they are 'equivalent' or 'not_equivalent'. ",
        "transfer_ori_acc": 69.0,
        "transfer_atk_acc": 66.5
    },
    {
        "dataset": "qnli",
        "type": "task",
        "origin_acc": 89.3,
        "origin_prompt": "Based on the provided context and question, decide if the information supports the answer by responding with 'entailment' or 'not_entailment'.",
        "atk_acc": 39.5,
        "atk_prompt": "Baesd on the prohided conteMt and questino, dRcide if the infzrmation suppoLrts the aOnswer by resXonding with 'entailment' or 'not_entailment'. ",
        "transfer_ori_acc": 83.0,
        "transfer_atk_acc": 80.0
    },
    {
        "dataset": "qnli",
        "type": "role",
        "origin_acc": 88.8,
        "origin_prompt": "In the capacity of a language evaluator, examine if the given context justifies the answer to the question and indicate your assessment with 'entailment' or 'not_entailment'.",
        "atk_acc": 44.5,
        "atk_prompt": "bn the cUapacity of a langtage valuator, Cxamine if the givcen contjxt jYustifies the anbwer to the qPuestion and idicate your assetssment with 'entailment' or 'not_entailment'. ",
        "transfer_ori_acc": 84.5,
        "transfer_atk_acc": 79.0
    },
    {
        "dataset": "qqp",
        "type": "task",
        "origin_acc": 88.1,
        "origin_prompt": "Are the following two questions equivalent or not? Answer me with \"equivalent\" or \"not_equivalent\".",
        "atk_acc": 77.3,
        "atk_prompt": "re the flolowing two questFons equivalent or not? Answe me with \"equivalent\" or \"not_equivalent\". ",
        "transfer_ori_acc": 82.5,
        "transfer_atk_acc": 83.0
    },
    {
        "dataset": "qqp",
        "type": "role",
        "origin_acc": 86.5,
        "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": 81.8,
        "atk_prompt": "As an instrument for question cotmparison evaluVtion, consider the questionPs and determbine if their maening is the same, responRing with 'equivalent' for similar questins or 'not_equivalent' for difserent questions. ",
        "transfer_ori_acc": 83.0,
        "transfer_atk_acc": 83.0
    },
    {
        "dataset": "rte",
        "type": "task",
        "origin_acc": 85.2,
        "origin_prompt": "Are the following two sentences entailment or not_entailment? Answer me with \"entailment\" or \"not_entailment\", just one word.",
        "atk_acc": 80.87,
        "atk_prompt": "Aer the followig mwo sentences entailment or not_entailment? nswer me with \"entailment\" or \"not_entailment\", just noe word. ",
        "transfer_ori_acc": 82.5,
        "transfer_atk_acc": 82.5
    },
    {
        "dataset": "rte",
        "type": "role",
        "origin_acc": 84.12,
        "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": 81.59,
        "atk_prompt": "Acting as an entailment detection instrument, dGetermine if the given pair of sentences demonstpates entailment or not_entailment. AVswer with 'entailment' or 'not_entailment'. ",
        "transfer_ori_acc": 83.5,
        "transfer_atk_acc": 83.5
    },
    {
        "dataset": "sst2",
        "type": "task",
        "origin_acc": 95.3,
        "origin_prompt": "Considering the given phrase, would you say it carries a 'positive' or 'negative' connotation?",
        "atk_acc": 93.92,
        "atk_prompt": "Considering the given phraes, wouHd you Fay it carries a 'positive' or 'negative' connotavtion? ",
        "transfer_ori_acc": 85.5,
        "transfer_atk_acc": 87.0
    },
    {
        "dataset": "sst2",
        "type": "role",
        "origin_acc": 95.41,
        "origin_prompt": "Acting as a sentiment evaluator, identify if the given sentence is 'positive' or 'negative'.",
        "atk_acc": 94.61,
        "atk_prompt": "Acting as a seniment valuator, dientify if the giveIn sentence is 'positive' or 'negative'. ",
        "transfer_ori_acc": 96.0,
        "transfer_atk_acc": 96.0
    },
    {
        "dataset": "wnli",
        "type": "task",
        "origin_acc": 64.79,
        "origin_prompt": "Assess the connection between the following sentences and classify it as 'entailment' or 'not_entailment'.",
        "atk_acc": 54.93,
        "atk_prompt": "Assses the connection between the followoing sentence and classify it as 'entailment' or 'not_entailment'. ",
        "transfer_ori_acc": 63.38028169014085,
        "transfer_atk_acc": 61.97183098591549
    },
    {
        "dataset": "wnli",
        "type": "role",
        "origin_acc": 66.2,
        "origin_prompt": "In the capacity of an entailment assessment system, indicate if the link between the following sentences is 'entailment' or 'not_entailment'.",
        "atk_acc": 56.34,
        "atk_prompt": "In the capaciy of an entailment assessment system, inDdicate if the liQk between the followign sentences is 'entailment' or 'not_entailment'. ",
        "transfer_ori_acc": 64.7887323943662,
        "transfer_atk_acc": 69.01408450704226
    },
    {
        "dataset": "mmlu",
        "type": "task",
        "origin_acc": 46.81,
        "origin_prompt": "In relation to the multiple-choice question on {}, please provide the accurate answer by choosing 'A', 'B', 'C', or 'D'.",
        "atk_acc": 43.44,
        "atk_prompt": "In relation to the ultiple-choice question on {}, lease rovide the accuraet answer by choosieg 'A', 'B', 'C', or 'D'. ",
        "transfer_ori_acc": 68.0,
        "transfer_atk_acc": 64.5
    },
    {
        "dataset": "mmlu",
        "type": "role",
        "origin_acc": 46.99,
        "origin_prompt": "Considering your familiarity with {}, attend to the following multiple-choice question by picking 'A', 'B', 'C', or 'D'.",
        "atk_acc": 43.44,
        "atk_prompt": "Considering your familiarity with {}, attePd to the following multiple-hcoice question by pickiGng 'A', 'B', 'C', or 'D'.",
        "transfer_ori_acc": 65.5,
        "transfer_atk_acc": 64.0
    },
    {
        "dataset": "squad_v2",
        "type": "task",
        "origin_acc": 87.91,
        "origin_prompt": "From the context, provide the most precise answer. If the answer is not in the context, respond with 'unanswerable'.",
        "atk_acc": 86.55,
        "atk_prompt": "Frmo the context, provide the most precise answer. If the answer is not in the context, respond with 'unanswerable'.",
        "transfer_ori_acc": 68.83640054239395,
        "transfer_atk_acc": 72.44751165350506
    },
    {
        "dataset": "squad_v2",
        "type": "role",
        "origin_acc": 87.05,
        "origin_prompt": "As a subject matter expert, extract the correct answer from the context. If an answer is not present, indicate 'unanswerable'.",
        "atk_acc": 86.59,
        "atk_prompt": "As a subject matter expert, extract the ocrrect anser from the contNext. If an answer is not present, indicate 'unanswerable'.",
        "transfer_ori_acc": 73.51286878855532,
        "transfer_atk_acc": 72.26636529205179
    },
    {
        "dataset": "iwslt",
        "type": "task",
        "origin_acc": 0.22,
        "origin_prompt": "Convert the following sentence from its original {} language to the target language {}.",
        "atk_acc": 0.21,
        "atk_prompt": "tonvert the following senvtence from its original {} language to the target language {}. ",
        "transfer_ori_acc": 0.23976066777257665,
        "transfer_atk_acc": 0.24198626199427362
    },
    {
        "dataset": "iwslt",
        "type": "role",
        "origin_acc": 0.22,
        "origin_prompt": "In the role of a language expert, perform a machine translation for the provided sentence, changing it from {} to {}.",
        "atk_acc": 0.14,
        "atk_prompt": "In the role of a langauge expert, perforF a machine kranslation for the pLovided senteSce, changing it from {} to {}. ",
        "transfer_ori_acc": 0.24585246891494666,
        "transfer_atk_acc": 0.2401658466423436
    },
    {
        "dataset": "un_multi",
        "type": "task",
        "origin_acc": 0.31,
        "origin_prompt": "Translate the provided sentence from {} to {} while maintaining the original meaning and context.",
        "atk_acc": 0.3,
        "atk_prompt": "Translate the proviWded entence from {} to {} while maintaining the oriinal meanin and conEtext. ",
        "transfer_ori_acc": 0.3480112011950064,
        "transfer_atk_acc": 0.34622353749471374
    },
    {
        "dataset": "un_multi",
        "type": "role",
        "origin_acc": 0.31,
        "origin_prompt": "Taking on the role of a certified translator, perform a translation of the given sentence from {} to {}.",
        "atk_acc": 0.26,
        "atk_prompt": "Taking on the roEle of a certifLed ltranslator, perofrm a trasnlation of the giDven senence from {} to {}. ",
        "transfer_ori_acc": 0.3487924607341456,
        "transfer_atk_acc": 0.3482747678030168
    },
    {
        "dataset": "math",
        "type": "task",
        "origin_acc": 17.5,
        "origin_prompt": "Figure out the solution for the following mathematical task with {}.",
        "atk_acc": 15.62,
        "atk_prompt": "Figure out the slution for the following mathemaitcal task with {}. ",
        "transfer_ori_acc": 20.0,
        "transfer_atk_acc": 21.25
    },
    {
        "dataset": "math",
        "type": "role",
        "origin_acc": 17.5,
        "origin_prompt": "As a mathematics instructor, calculate the answer to the following problem related to {}.",
        "atk_acc": 15.0,
        "atk_prompt": "sA a mathematics instructor, calculate the anvwer to the following problem relDated to {}. ",
        "transfer_ori_acc": 21.875,
        "transfer_atk_acc": 21.25
    }
]