results_transfer/google-flan-t5-large_chatgpt/textfooler_0_shot.json

[
    {
        "dataset": "cola",
        "type": "task",
        "origin_acc": 77.5,
        "origin_prompt": "Determine if the grammar of the given sentence is 'Acceptable' or 'Unacceptable':",
        "atk_acc": 31.0,
        "atk_prompt": "Establishes if the jargon of the made punishments is 'Acceptable' or 'Unacceptable':",
        "transfer_ori_acc": 75.5,
        "transfer_atk_acc": 28.499999999999996
    },
    {
        "dataset": "cola",
        "type": "role",
        "origin_acc": 76.3,
        "origin_prompt": "As an instrument for grammar evaluation, consider the sentence and determine if its grammar is correct, responding with 'acceptable' for correct grammar or 'unacceptable' for incorrect grammar:",
        "atk_acc": 30.8,
        "atk_prompt": "Since an apparatus for language measured, envisage the convicts and identify if its language is correct, reaction with 'acceptable' for accurate jargon or 'unacceptable' for unsound pronunciation:",
        "transfer_ori_acc": 79.5,
        "transfer_atk_acc": 71.0
    },
    {
        "dataset": "mrpc",
        "type": "task",
        "origin_acc": 82.11,
        "origin_prompt": "Do these two sentences have the same underlying meaning? Respond with 'equivalent' or 'not_equivalent'.",
        "atk_acc": 53.68,
        "atk_prompt": "Ca these two condemning ont the same main meaning? Reactions with 'equivalent' or 'not_equivalent'. ",
        "transfer_ori_acc": 73.0,
        "transfer_atk_acc": 46.5
    },
    {
        "dataset": "mrpc",
        "type": "role",
        "origin_acc": 81.62,
        "origin_prompt": "As a language comparison expert, examine the given pair of sentences and decide if their meanings align, answering with 'equivalent' or 'not_equivalent'.",
        "atk_acc": 12.01,
        "atk_prompt": "As a language compared professional, reviews the given torque of sentences and picked if their sens unify, address with 'equivalent' or 'not_equivalent'. ",
        "transfer_ori_acc": 73.0,
        "transfer_atk_acc": 75.5
    },
    {
        "dataset": "qnli",
        "type": "task",
        "origin_acc": 89.8,
        "origin_prompt": "Evaluate whether the given context supports the answer to the question by responding with 'entailment' or 'not_entailment'.",
        "atk_acc": 41.4,
        "atk_prompt": "Estimation whether the gave backgrounds perpetuates the answered to the trouble by responses with 'entailment' or 'not_entailment'. ",
        "transfer_ori_acc": 77.5,
        "transfer_atk_acc": 64.5
    },
    {
        "dataset": "qnli",
        "type": "role",
        "origin_acc": 89.4,
        "origin_prompt": "As a semantic interpreter, assess whether the provided context supports the answer to the given question and answer with 'entailment' or 'not_entailment'.",
        "atk_acc": 3.3,
        "atk_prompt": "Iike a semantic performers, valuing whether the afforded ambient perpetuates the answer to the rendered item and cope with 'entailment' or 'not_entailment'. ",
        "transfer_ori_acc": 67.0,
        "transfer_atk_acc": 2.0
    },
    {
        "dataset": "qqp",
        "type": "task",
        "origin_acc": 87.7,
        "origin_prompt": "Assess whether the following statements are identical in meaning by answering 'equivalent' or 'not_equivalent'.",
        "atk_acc": 18.9,
        "atk_prompt": "Valuing whether the later languages are comparable in sinn by cope 'equivalent' or 'not_equivalent'. ",
        "transfer_ori_acc": 82.0,
        "transfer_atk_acc": 42.0
    },
    {
        "dataset": "qqp",
        "type": "role",
        "origin_acc": 86.9,
        "origin_prompt": "In the role of a question similarity analyzer, examine the meaning of the provided questions and decide if they are equivalent, answering with 'equivalent' for equivalent questions or 'not_equivalent' for different questions.",
        "atk_acc": 73.8,
        "atk_prompt": "About the rol of a question likeness analyzer, examine the mean of the conferred topic and identifying if they are equivalent, retaliated with 'equivalent' for equivalent trouble or 'not_equivalent' for other topics. ",
        "transfer_ori_acc": 81.5,
        "transfer_atk_acc": 77.5
    },
    {
        "dataset": "rte",
        "type": "task",
        "origin_acc": 86.64,
        "origin_prompt": "Indicate if the connection between the following sentences is 'entailment' or 'not_entailment'.",
        "atk_acc": 80.87,
        "atk_prompt": "Portrays if the login between the following punishments is 'entailment' or 'not_entailment'.",
        "transfer_ori_acc": 76.5,
        "transfer_atk_acc": 74.5
    },
    {
        "dataset": "rte",
        "type": "role",
        "origin_acc": 84.84,
        "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": 79.06,
        "atk_prompt": "About the capacity of an entailment weighed system, specified if the link between the following phrases is 'entailment' or 'not_entailment':",
        "transfer_ori_acc": 78.0,
        "transfer_atk_acc": 74.0
    },
    {
        "dataset": "sst2",
        "type": "task",
        "origin_acc": 94.95,
        "origin_prompt": "Given the context of this text, indicate if the emotion conveyed is 'positive' or 'negative':",
        "atk_acc": 84.29,
        "atk_prompt": "Made the background of this version, depicts if the passion recharged is 'positive' or 'negative': ",
        "transfer_ori_acc": 86.5,
        "transfer_atk_acc": 34.5
    },
    {
        "dataset": "sst2",
        "type": "role",
        "origin_acc": 95.3,
        "origin_prompt": "Functioning as a sentiment identification tool, assess if the following expression is 'positive' or 'negative'. Classify:",
        "atk_acc": 25.46,
        "atk_prompt": "Functions as a emotion defining instrumentation, valuing if the next voicing is 'positive' or 'negative'. Classification: ",
        "transfer_ori_acc": 92.0,
        "transfer_atk_acc": 62.5
    },
    {
        "dataset": "wnli",
        "type": "task",
        "origin_acc": 66.2,
        "origin_prompt": "Are the following two sentences entailment or not_entailment? Answer me with \"entailment\" or \"not_entailment\", just one word.",
        "atk_acc": 56.34,
        "atk_prompt": "Be the following two phrases entailment or not_entailment? Responded me with \"entailment\" or \"not_entailment\", just one verb. ",
        "transfer_ori_acc": 64.7887323943662,
        "transfer_atk_acc": 61.97183098591549
    },
    {
        "dataset": "wnli",
        "type": "role",
        "origin_acc": 64.79,
        "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": "Among the capacity of an entailment analysis system, indicate if the attach between the subsequently sentences is 'entailment' or 'not_entailment':",
        "transfer_ori_acc": 56.33802816901409,
        "transfer_atk_acc": 53.52112676056338
    },
    {
        "dataset": "mmlu",
        "type": "task",
        "origin_acc": 45.74,
        "origin_prompt": "For each multiple-choice question about {}, identify the correct answer by selecting 'A', 'B', 'C', or 'D'.",
        "atk_acc": 37.06,
        "atk_prompt": "By any multiple-choice question about {}, locate the corrected riposte by akhtar 'A', 'B', 'C', or 'D'. ",
        "transfer_ori_acc": 60.0,
        "transfer_atk_acc": 57.99999999999999
    },
    {
        "dataset": "mmlu",
        "type": "role",
        "origin_acc": 44.86,
        "origin_prompt": "Utilizing your expertise in {}, answer the following multiple-choice question by picking 'A', 'B', 'C', or 'D'.",
        "atk_acc": 40.96,
        "atk_prompt": "Utilise your expertise in {}, meet the next multiple-choice question by collection 'A', 'B', 'C', or 'D'.",
        "transfer_ori_acc": 60.0,
        "transfer_atk_acc": 62.5
    },
    {
        "dataset": "squad_v2",
        "type": "task",
        "origin_acc": 87.65,
        "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": 84.09,
        "atk_prompt": "Please subtract the most adjust answered from the context. Until there isn't an replied in the context, answered with 'unanswerable'.",
        "transfer_ori_acc": 68.9823963074465,
        "transfer_atk_acc": 70.0222411877797
    },
    {
        "dataset": "squad_v2",
        "type": "role",
        "origin_acc": 88.05,
        "origin_prompt": "As an authority on the context, locate the most accurate answer. If the context doesn't contain the answer, mention 'unanswerable'.",
        "atk_acc": 77.31,
        "atk_prompt": "As an authority on the context, find the most proper rebuttal. Though the context doesn't incorporated the answering, speaks 'unanswerable'.",
        "transfer_ori_acc": 58.339251638716306,
        "transfer_atk_acc": 13.16285232916677
    },
    {
        "dataset": "iwslt",
        "type": "task",
        "origin_acc": 0.14,
        "origin_prompt": "Please perform a translation of the given sentence, converting it from {} to {}:",
        "atk_acc": 0.13,
        "atk_prompt": "Please accomplishing a translators of the given judging, converting it from {} to {}:",
        "transfer_ori_acc": 0.21831949334978593,
        "transfer_atk_acc": 0.2239880425221272
    },
    {
        "dataset": "iwslt",
        "type": "role",
        "origin_acc": 0.14,
        "origin_prompt": "In the role of a language expert, perform a machine translation for the provided sentence, changing it from {} to {}:",
        "atk_acc": 0.06,
        "atk_prompt": "Under the features of a parlance specializing, realization a typewriter translator for the envisaged chastisement, altering it from {} to {}: ",
        "transfer_ori_acc": 0.21989352460304576,
        "transfer_atk_acc": 0.21750678591307532
    },
    {
        "dataset": "un_multi",
        "type": "task",
        "origin_acc": 0.27,
        "origin_prompt": "Convert the following sentence from its original {} language to the target language {}:",
        "atk_acc": 0.11,
        "atk_prompt": "Transformations the later sanctions from its preliminary {} linguistics to the fated parlance {}:",
        "transfer_ori_acc": 0.3247743039495714,
        "transfer_atk_acc": 0.32716823822221747
    },
    {
        "dataset": "un_multi",
        "type": "role",
        "origin_acc": 0.27,
        "origin_prompt": "In the role of a language expert, perform a machine translation for the provided sentence, changing it from {} to {}:",
        "atk_acc": 0.15,
        "atk_prompt": "Under the role of a language skilled, performed a machine interpreters for the furnished condemned, transform it from {} to {}: ",
        "transfer_ori_acc": 0.3345754849723755,
        "transfer_atk_acc": 0.34235722522451423
    },
    {
        "dataset": "math",
        "type": "task",
        "origin_acc": 13.75,
        "origin_prompt": "Work out the answer to this math problem featuring {}:",
        "atk_acc": 1.88,
        "atk_prompt": "Work out the address to this math problem idiosyncratic {}:",
        "transfer_ori_acc": 6.25,
        "transfer_atk_acc": 6.25
    },
    {
        "dataset": "math",
        "type": "role",
        "origin_acc": 13.12,
        "origin_prompt": "As a mathematics instructor, calculate the answer to the following problem related to {}:",
        "atk_acc": 1.25,
        "atk_prompt": "As a mathematics prof, calculate the address to the following problem related to {}: ",
        "transfer_ori_acc": 5.0,
        "transfer_atk_acc": 4.375
    }
]