Spaces:
Runtime error
Runtime error
| [ | |
| { | |
| "dataset": "cola", | |
| "type": "task", | |
| "origin_acc": 78.5, | |
| "origin_prompt": "Review the sentence below and identify whether its grammar is 'Acceptable' or 'Unacceptable':", | |
| "atk_acc": 72.5, | |
| "atk_prompt": "Review the sentence below and identify whether its grammar is 'Acceptable' or 'Unacceptable' zexKUTWJYG:", | |
| "transfer_ori_acc": 86.0, | |
| "transfer_atk_acc": 84.7 | |
| }, | |
| { | |
| "dataset": "cola", | |
| "type": "role", | |
| "origin_acc": 79.0, | |
| "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": 45.0, | |
| "atk_prompt": "While performing grammar analysis, classify the grammar of the following sentence as 'acceptable' for correct grammar or 'unacceptable' for incorrect grammar zexKUTWJYG:", | |
| "transfer_ori_acc": 86.0, | |
| "transfer_atk_acc": 82.19999999999999 | |
| }, | |
| { | |
| "dataset": "mrpc", | |
| "type": "task", | |
| "origin_acc": 75.5, | |
| "origin_prompt": "Evaluate whether the two provided sentences convey the same meaning by answering 'equivalent' or 'not_equivalent'.", | |
| "atk_acc": 72.0, | |
| "atk_prompt": "Evaluate whether the two provided sentences convey the same meaning by answering 'equivalent' or 'not_equivalent' SvAp8RlOFn. ", | |
| "transfer_ori_acc": 86.27450980392157, | |
| "transfer_atk_acc": 85.7843137254902 | |
| }, | |
| { | |
| "dataset": "mrpc", | |
| "type": "role", | |
| "origin_acc": 75.5, | |
| "origin_prompt": "In your capacity as a semantic assessment tool, evaluate the provided sentences and classify their meanings as 'equivalent' or 'not_equivalent'.", | |
| "atk_acc": 73.5, | |
| "atk_prompt": "In your capacity as a semantic assessment tool, evaluate the provided sentences and classify their meanings as 'equivalent' or 'not_equivalent' Kw6nrs57gH. ", | |
| "transfer_ori_acc": 83.33333333333334, | |
| "transfer_atk_acc": 83.82352941176471 | |
| }, | |
| { | |
| "dataset": "qnli", | |
| "type": "task", | |
| "origin_acc": 78.0, | |
| "origin_prompt": "Evaluate whether the given context supports the answer to the question by responding with 'entailment' or 'not_entailment'.", | |
| "atk_acc": 75.5, | |
| "atk_prompt": "Evaluate whether the given context supports the answer to the question by responding with 'entailment' or 'not_entailment' ItGDrrA1Sc. ", | |
| "transfer_ori_acc": 93.89999999999999, | |
| "transfer_atk_acc": 94.39999999999999 | |
| }, | |
| { | |
| "dataset": "qnli", | |
| "type": "role", | |
| "origin_acc": 78.0, | |
| "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": 74.5, | |
| "atk_prompt": "As a semantic researcher, evaluate whether the provided context supports the answer to the question and choose 'entailment' or 'not_entailment' 6a4Yn3RGVc. ", | |
| "transfer_ori_acc": 94.69999999999999, | |
| "transfer_atk_acc": 94.3 | |
| }, | |
| { | |
| "dataset": "qqp", | |
| "type": "task", | |
| "origin_acc": 81.5, | |
| "origin_prompt": "Assess whether the following statements are identical in meaning by answering 'equivalent' or 'not_equivalent'.", | |
| "atk_acc": 78.0, | |
| "atk_prompt": "Assess whether the following statements are identical in meaning by answering 'equivalent' or 'not_equivalent' iia2yL9Uzm. ", | |
| "transfer_ori_acc": 87.7, | |
| "transfer_atk_acc": 88.4 | |
| }, | |
| { | |
| "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": 80.5, | |
| "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 Cev0s49fbe. ", | |
| "transfer_ori_acc": 88.3, | |
| "transfer_atk_acc": 88.5 | |
| }, | |
| { | |
| "dataset": "rte", | |
| "type": "task", | |
| "origin_acc": 82.5, | |
| "origin_prompt": "Determine if the given pair of sentences displays entailment or not_entailment. Respond with 'entailment' or 'not_entailment'.", | |
| "atk_acc": 80.0, | |
| "atk_prompt": "Determine if the given pair of sentences displays entailment or not_entailment. Respond with 'entailment' or 'not_entailment' MSAddJ4D2a.", | |
| "transfer_ori_acc": 93.50180505415162, | |
| "transfer_atk_acc": 93.50180505415162 | |
| }, | |
| { | |
| "dataset": "rte", | |
| "type": "role", | |
| "origin_acc": 81.5, | |
| "origin_prompt": "As an instrument for entailment evaluation, consider the two sentences and determine if their relationship is 'entailment' or 'not_entailment'. Respond with 'entailment' or 'not_entailment':", | |
| "atk_acc": 80.0, | |
| "atk_prompt": "As an instrument for entailment evaluation, consider the two sentences and determine if their relationship is 'entailment' or 'not_entailment'. Respond with 'entailment' or 'not_entailment' 6a4Yn3RGVc:", | |
| "transfer_ori_acc": 93.50180505415162, | |
| "transfer_atk_acc": 94.22382671480143 | |
| }, | |
| { | |
| "dataset": "sst2", | |
| "type": "task", | |
| "origin_acc": 93.0, | |
| "origin_prompt": "Determine the overall sentiment of this sentence, categorizing it as 'positive' or 'negative':", | |
| "atk_acc": 90.0, | |
| "atk_prompt": "Determine the overall sentiment of this sentence, categorizing it as 'positive' or 'negative' AMsRIKZniY: ", | |
| "transfer_ori_acc": 96.67431192660551, | |
| "transfer_atk_acc": 96.3302752293578 | |
| }, | |
| { | |
| "dataset": "sst2", | |
| "type": "role", | |
| "origin_acc": 92.5, | |
| "origin_prompt": "Functioning as a sentiment identification tool, assess if the following expression is 'positive' or 'negative'. Classify:", | |
| "atk_acc": 92.0, | |
| "atk_prompt": "Functioning as a sentiment identification tool, assess if the following expression is 'positive' or 'negative'. Classify Cev0s49fbe: ", | |
| "transfer_ori_acc": 95.9862385321101, | |
| "transfer_atk_acc": 96.3302752293578 | |
| }, | |
| { | |
| "dataset": "wnli", | |
| "type": "task", | |
| "origin_acc": 64.79, | |
| "origin_prompt": "Are the following two sentences entailment or not_entailment? Answer me with \"entailment\" or \"not_entailment\", just one word.", | |
| "atk_acc": 59.15, | |
| "atk_prompt": "Are the following two sentences entailment or not_entailment? Answer me with \"entailment\" or \"not_entailment\", just one word zexKUTWJYG. ", | |
| "transfer_ori_acc": 78.87323943661971, | |
| "transfer_atk_acc": 78.87323943661971 | |
| }, | |
| { | |
| "dataset": "wnli", | |
| "type": "role", | |
| "origin_acc": 63.38, | |
| "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": 57.75, | |
| "atk_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' 5XeflW1ZJc:", | |
| "transfer_ori_acc": 77.46478873239437, | |
| "transfer_atk_acc": 78.87323943661971 | |
| }, | |
| { | |
| "dataset": "mmlu", | |
| "type": "task", | |
| "origin_acc": 64.0, | |
| "origin_prompt": "Regarding the following multiple-choice question on {}, pick the correct answer from the options 'A', 'B', 'C', or 'D'.", | |
| "atk_acc": 58.0, | |
| "atk_prompt": "Regarding the following multiple-choice question on {}, pick the correct answer from the options 'A', 'B', 'C', or 'D' Pbl3tYuoRo. ", | |
| "transfer_ori_acc": 52.304964539007095, | |
| "transfer_atk_acc": 52.4822695035461 | |
| }, | |
| { | |
| "dataset": "mmlu", | |
| "type": "role", | |
| "origin_acc": 61.5, | |
| "origin_prompt": "As a skilled person in the field of {}, please respond to the multiple-choice question by choosing 'A', 'B', 'C', or 'D'.", | |
| "atk_acc": 58.0, | |
| "atk_prompt": "As a skilled person in the field of {}, please respond to the multiple-choice question by choosing 'A', 'B', 'C', or 'D' IhuBIhoPGc.", | |
| "transfer_ori_acc": 52.4822695035461, | |
| "transfer_atk_acc": 53.72340425531915 | |
| }, | |
| { | |
| "dataset": "squad_v2", | |
| "type": "task", | |
| "origin_acc": 69.16, | |
| "origin_prompt": "Based on the given context, provide the best possible answer. If there's no answer available in the context, respond with 'unanswerable'.", | |
| "atk_acc": 64.99, | |
| "atk_prompt": "Based on the given context, provide the best possible answer. If there's no answer available in the context, respond with 'unanswerable' ItGDrrA1Sc.", | |
| "transfer_ori_acc": 89.38229949874687, | |
| "transfer_atk_acc": 89.31979949874687 | |
| }, | |
| { | |
| "dataset": "squad_v2", | |
| "type": "role", | |
| "origin_acc": 64.31, | |
| "origin_prompt": "As an expert with a deep understanding of the context, find the best answer. If the context doesn't include an answer, say 'unanswerable'.", | |
| "atk_acc": 60.2, | |
| "atk_prompt": "As an expert with a deep understanding of the context, find the best answer. If the context doesn't include an answer, say 'unanswerable' d6ZQ3u0GBQ.", | |
| "transfer_ori_acc": 89.44479949874687, | |
| "transfer_atk_acc": 89.81979949874687 | |
| }, | |
| { | |
| "dataset": "iwslt", | |
| "type": "task", | |
| "origin_acc": 0.22, | |
| "origin_prompt": "Translate the provided sentence from {} to {} while maintaining the original meaning and context:", | |
| "atk_acc": 0.21, | |
| "atk_prompt": "Translate the provided sentence from {} to {} while maintaining the original meaning and context zq0DcZ5dnI:", | |
| "transfer_ori_acc": 0.1697518407093131, | |
| "transfer_atk_acc": 0.17419805969910362 | |
| }, | |
| { | |
| "dataset": "iwslt", | |
| "type": "role", | |
| "origin_acc": 0.22, | |
| "origin_prompt": "In the capacity of a proficient translator, please change the following sentence from {} to {}:", | |
| "atk_acc": 0.21, | |
| "atk_prompt": "In the capacity of a proficient translator, please change the following sentence from {} to SFPCqpiClT {}: ", | |
| "transfer_ori_acc": 0.17223574608131062, | |
| "transfer_atk_acc": 0.16640042157073662 | |
| }, | |
| { | |
| "dataset": "un_multi", | |
| "type": "task", | |
| "origin_acc": 0.34, | |
| "origin_prompt": "Perform a machine translation for the provided sentence, changing it from {} to {}:", | |
| "atk_acc": 0.33, | |
| "atk_prompt": "Perform a machine translation for the provided sentence, changing it from {} to Kw6nrs57gH {}:", | |
| "transfer_ori_acc": 0.3102455120610509, | |
| "transfer_atk_acc": 0.30087524214938727 | |
| }, | |
| { | |
| "dataset": "un_multi", | |
| "type": "role", | |
| "origin_acc": 0.34, | |
| "origin_prompt": "While acting as an experienced language expert, translate the following text from {} to {}:", | |
| "atk_acc": 0.33, | |
| "atk_prompt": "While acting as an experienced language expert, translate the following text from {} to Kw6nrs57gH {}: ", | |
| "transfer_ori_acc": 0.3133010160127483, | |
| "transfer_atk_acc": 0.2966985644521811 | |
| }, | |
| { | |
| "dataset": "math", | |
| "type": "task", | |
| "origin_acc": 6.88, | |
| "origin_prompt": "Calculate the answer to the following math query about {}:", | |
| "atk_acc": 5.0, | |
| "atk_prompt": "Calculate the answer to the following math query about 6a4Yn3RGVc {}:", | |
| "transfer_ori_acc": 14.374999999999998, | |
| "transfer_atk_acc": 13.750000000000002 | |
| }, | |
| { | |
| "dataset": "math", | |
| "type": "role", | |
| "origin_acc": 5.0, | |
| "origin_prompt": "Embodying a mathematics advisor, find the answer to the following math problem with {}:", | |
| "atk_acc": 2.5, | |
| "atk_prompt": "Embodying a mathematics advisor, find the answer to the following math problem with 9vGXgnbWB8 {}: ", | |
| "transfer_ori_acc": 13.125, | |
| "transfer_atk_acc": 12.5 | |
| } | |
| ] |