Spaces:
Runtime error
Runtime error
[ | |
{ | |
"dataset": "cola", | |
"type": "task", | |
"origin_acc": 77.9, | |
"origin_prompt": "Examine the given sentence and decide if it is grammatically sound. Answer with either 'Acceptable' or 'Unacceptable':", | |
"atk_acc": 62.6, | |
"atk_prompt": "Examine the given sentence and decide if it is grammatically sound. Answer with either 'Acceptable' or 'Unacceptable' IhuBIhoPGc:", | |
"transfer_ori_acc": 77.0, | |
"transfer_atk_acc": 75.0 | |
}, | |
{ | |
"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": 74.9, | |
"atk_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 IhuBIhoPGc:", | |
"transfer_ori_acc": 78.5, | |
"transfer_atk_acc": 72.0 | |
}, | |
{ | |
"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": 79.17, | |
"atk_prompt": "Do these two sentences have the same underlying meaning? Respond with 'equivalent' or 'not_equivalent' MSAddJ4D2a. ", | |
"transfer_ori_acc": 73.5, | |
"transfer_atk_acc": 75.0 | |
}, | |
{ | |
"dataset": "mrpc", | |
"type": "role", | |
"origin_acc": 82.6, | |
"origin_prompt": "As a semantic comparison expert, evaluate the given pair of sentences and determine if they are 'equivalent' or 'not_equivalent'.", | |
"atk_acc": 80.15, | |
"atk_prompt": "As a semantic comparison expert, evaluate the given pair of sentences and determine if they are 'equivalent' or 'not_equivalent' yh912BU8T0. ", | |
"transfer_ori_acc": 72.5, | |
"transfer_atk_acc": 74.0 | |
}, | |
{ | |
"dataset": "qnli", | |
"type": "task", | |
"origin_acc": 88.5, | |
"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": 87.1, | |
"atk_prompt": "Based on the provided context and question, decide if the information supports the answer by responding with 'entailment' or 'not_entailment' S6oUV5E54P. ", | |
"transfer_ori_acc": 78.0, | |
"transfer_atk_acc": 75.5 | |
}, | |
{ | |
"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": 88.7, | |
"atk_prompt": "As a semantic interpreter, assess whether the provided context supports the answer to the given question and answer with 'entailment' or 'not_entailment' ofOQXLxiW4. ", | |
"transfer_ori_acc": 67.5, | |
"transfer_atk_acc": 72.5 | |
}, | |
{ | |
"dataset": "qqp", | |
"type": "task", | |
"origin_acc": 87.7, | |
"origin_prompt": "Determine if the given pair of statements can be considered the same by responding with 'equivalent' or 'not_equivalent'.", | |
"atk_acc": 86.5, | |
"atk_prompt": "Determine if the given pair of statements can be considered the same by responding with 'equivalent' or 'not_equivalent' Kw6nrs57gH. ", | |
"transfer_ori_acc": 81.5, | |
"transfer_atk_acc": 81.5 | |
}, | |
{ | |
"dataset": "qqp", | |
"type": "role", | |
"origin_acc": 86.9, | |
"origin_prompt": "Functioning as a question similarity evaluation tool, analyze the given questions and decide if they share the same meaning, responding with 'equivalent' or 'not_equivalent'.", | |
"atk_acc": 86.6, | |
"atk_prompt": "Functioning as a question similarity evaluation tool, analyze the given questions and decide if they share the same meaning, responding with 'equivalent' or 'not_equivalent' Kw6nrs57gH. ", | |
"transfer_ori_acc": 81.5, | |
"transfer_atk_acc": 82.0 | |
}, | |
{ | |
"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": 83.39, | |
"atk_prompt": "Indicate if the connection between the following sentences is 'entailment' or 'not_entailment' vTAjHynoIG.", | |
"transfer_ori_acc": 76.5, | |
"transfer_atk_acc": 77.5 | |
}, | |
{ | |
"dataset": "rte", | |
"type": "role", | |
"origin_acc": 84.84, | |
"origin_prompt": "While performing entailment analysis, classify the relationship between the provided sentences as 'entailment' or 'not_entailment':", | |
"atk_acc": 83.75, | |
"atk_prompt": "While performing entailment analysis, classify the relationship between the provided sentences as 'entailment' or 'not_entailment' CuVpbbkC4c:", | |
"transfer_ori_acc": 79.0, | |
"transfer_atk_acc": 80.5 | |
}, | |
{ | |
"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": 93.58, | |
"atk_prompt": "Given the context of this text, indicate if the emotion conveyed is 'positive' or 'negative' LkF0FZxMZ4: ", | |
"transfer_ori_acc": 86.5, | |
"transfer_atk_acc": 87.0 | |
}, | |
{ | |
"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": 94.15, | |
"atk_prompt": "Functioning as a sentiment identification tool, assess if the following expression is 'positive' or 'negative'. Classify ItGDrrA1Sc: ", | |
"transfer_ori_acc": 92.0, | |
"transfer_atk_acc": 93.0 | |
}, | |
{ | |
"dataset": "wnli", | |
"type": "task", | |
"origin_acc": 64.79, | |
"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' Kw6nrs57gH.", | |
"transfer_ori_acc": 52.112676056338024, | |
"transfer_atk_acc": 57.74647887323944 | |
}, | |
{ | |
"dataset": "wnli", | |
"type": "role", | |
"origin_acc": 66.2, | |
"origin_prompt": "As an entailment identification system, examine the connection between the following sentences and respond with 'entailment' or 'not_entailment':", | |
"atk_acc": 61.97, | |
"atk_prompt": "As an entailment identification system, examine the connection between the following sentences and respond with 'entailment' or 'not_entailment' SFPCqpiClT:", | |
"transfer_ori_acc": 50.70422535211267, | |
"transfer_atk_acc": 53.52112676056338 | |
}, | |
{ | |
"dataset": "mmlu", | |
"type": "task", | |
"origin_acc": 45.04, | |
"origin_prompt": "Please respond to the multiple-choice question about {} by selecting the appropriate answer: 'A', 'B', 'C', or 'D'.", | |
"atk_acc": 43.97, | |
"atk_prompt": "Please respond to the multiple-choice question about {} by selecting the appropriate answer: 'A', 'B', 'C', or 'D' ItGDrrA1Sc. ", | |
"transfer_ori_acc": 62.0, | |
"transfer_atk_acc": 60.5 | |
}, | |
{ | |
"dataset": "mmlu", | |
"type": "role", | |
"origin_acc": 44.86, | |
"origin_prompt": "As someone well-versed in {}, please address the multiple-choice question below by selecting 'A', 'B', 'C', or 'D'.", | |
"atk_acc": 43.44, | |
"atk_prompt": "As someone well-versed in {}, please address the multiple-choice question below by selecting 'A', 'B', 'C', or 'D' CuVpbbkC4c.", | |
"transfer_ori_acc": 59.5, | |
"transfer_atk_acc": 61.0 | |
}, | |
{ | |
"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": 86.82, | |
"atk_prompt": "Please derive the most fitting answer from the context. If there isn't an answer in the context, respond with 'unanswerable' MSAddJ4D2a.", | |
"transfer_ori_acc": 69.02399528817593, | |
"transfer_atk_acc": 69.50796630082341 | |
}, | |
{ | |
"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": 87.15, | |
"atk_prompt": "As an authority on the context, locate the most accurate answer. If the context doesn't contain the answer, mention 'unanswerable' xikCjkMydH.", | |
"transfer_ori_acc": 58.75591830538296, | |
"transfer_atk_acc": 61.29287775116594 | |
}, | |
{ | |
"dataset": "iwslt", | |
"type": "task", | |
"origin_acc": 0.14, | |
"origin_prompt": "Please perform a translation of the given sentence, converting it from {} to {}:", | |
"atk_acc": 0.1, | |
"atk_prompt": "Please perform a translation of the given sentence, converting it from {} to mzjVogkRhM {}:", | |
"transfer_ori_acc": 0.21840008360286153, | |
"transfer_atk_acc": 0.22514742934128096 | |
}, | |
{ | |
"dataset": "iwslt", | |
"type": "role", | |
"origin_acc": 0.14, | |
"origin_prompt": "Taking on the role of a certified translator, perform a translation of the given sentence from {} to {}:", | |
"atk_acc": 0.08, | |
"atk_prompt": "Taking on the role of a certified translator, perform a translation of the given sentence from {} to zexKUTWJYG {}: ", | |
"transfer_ori_acc": 0.22600539164221617, | |
"transfer_atk_acc": 0.22448676631201958 | |
}, | |
{ | |
"dataset": "un_multi", | |
"type": "task", | |
"origin_acc": 0.27, | |
"origin_prompt": "Accurately translate the sentence from {} to {}, ensuring the meaning remains intact:", | |
"atk_acc": 0.21, | |
"atk_prompt": "Accurately translate the sentence from {} to {}, ensuring the meaning remains intact EAB4KP2NVY:", | |
"transfer_ori_acc": 0.3279360242319025, | |
"transfer_atk_acc": 0.3291687239207952 | |
}, | |
{ | |
"dataset": "un_multi", | |
"type": "role", | |
"origin_acc": 0.27, | |
"origin_prompt": "Assuming the role of an expert language translator, translate the given text from {} to {}:", | |
"atk_acc": 0.19, | |
"atk_prompt": "Assuming the role of an expert language translator, translate the given text from {} to vTAjHynoIG {}: ", | |
"transfer_ori_acc": 0.3317016758714199, | |
"transfer_atk_acc": 0.3316999414372619 | |
}, | |
{ | |
"dataset": "math", | |
"type": "task", | |
"origin_acc": 16.25, | |
"origin_prompt": "Evaluate the following mathematical problem that includes {}:", | |
"atk_acc": 10.62, | |
"atk_prompt": "Evaluate the following mathematical problem that includes is77sOXAu8 {}:", | |
"transfer_ori_acc": 4.375, | |
"transfer_atk_acc": 4.375 | |
}, | |
{ | |
"dataset": "math", | |
"type": "role", | |
"origin_acc": 14.37, | |
"origin_prompt": "As a math guru, evaluate the following mathematical task regarding {}:", | |
"atk_acc": 10.0, | |
"atk_prompt": "As a math guru, evaluate the following mathematical task regarding KjPJJ2a7RB {}: ", | |
"transfer_ori_acc": 4.375, | |
"transfer_atk_acc": 2.5 | |
} | |
] |