Spaces:
Runtime error
Runtime error
| [ | |
| { | |
| "dataset": "cola", | |
| "type": "task", | |
| "origin_acc": 79.0, | |
| "origin_prompt": "Review the sentence below and identify whether its grammar is 'Acceptable' or 'Unacceptable':", | |
| "atk_acc": 74.5, | |
| "atk_prompt": "Review the sentece below and identify whether its grammar is 'Acceptable' or 'Unacceptable':", | |
| "transfer_ori_acc": 86.0, | |
| "transfer_atk_acc": 86.3 | |
| }, | |
| { | |
| "dataset": "cola", | |
| "type": "role", | |
| "origin_acc": 79.5, | |
| "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": 0.0, | |
| "atk_prompt": "nhile performing grammr analysis, classify the rgammar of the fllowing sentenZe as 'acceptable' for corFect Xrammar or 'unacceptable' for incorrect gramUar:", | |
| "transfer_ori_acc": 86.0, | |
| "transfer_atk_acc": 84.39999999999999 | |
| }, | |
| { | |
| "dataset": "mrpc", | |
| "type": "task", | |
| "origin_acc": 74.0, | |
| "origin_prompt": "Evaluate whether the two provided sentences convey the same meaning by answering 'equivalent' or 'not_equivalent'.", | |
| "atk_acc": 70.0, | |
| "atk_prompt": "Evaluate whether the two provRided sentnces convey the same meaning by answering 'equivalent' or 'not_equivalent'. ", | |
| "transfer_ori_acc": 86.27450980392157, | |
| "transfer_atk_acc": 84.06862745098039 | |
| }, | |
| { | |
| "dataset": "mrpc", | |
| "type": "role", | |
| "origin_acc": 76.0, | |
| "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": 53.0, | |
| "atk_prompt": "nI your capacity as a sematnic asseJssment tol, evaluate the prvoided senRtences and classify their meainngs as 'equivalent' or 'not_equivalent'. ", | |
| "transfer_ori_acc": 83.33333333333334, | |
| "transfer_atk_acc": 82.84313725490196 | |
| }, | |
| { | |
| "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": 50.0, | |
| "atk_prompt": "Exaluate whetxher the iven contet Supports the anwser to the queston by respEonding with 'entailment' or 'not_entailment'. ", | |
| "transfer_ori_acc": 93.89999999999999, | |
| "transfer_atk_acc": 94.39999999999999 | |
| }, | |
| { | |
| "dataset": "qnli", | |
| "type": "role", | |
| "origin_acc": 79.5, | |
| "origin_prompt": "As a textual inference expert, analyze if the answer to the question can be deduced from the provided context and select 'entailment' or 'not_entailment'.", | |
| "atk_acc": 19.5, | |
| "atk_prompt": "As a textula inference expert, aInalyze if the answer to the question can be deducud from the provided context and Melect 'entailment' or 'not_entailment'. ", | |
| "transfer_ori_acc": 93.30000000000001, | |
| "transfer_atk_acc": 93.2 | |
| }, | |
| { | |
| "dataset": "qqp", | |
| "type": "task", | |
| "origin_acc": 82.0, | |
| "origin_prompt": "Assess whether the following statements are identical in meaning by answering 'equivalent' or 'not_equivalent'.", | |
| "atk_acc": 45.0, | |
| "atk_prompt": "Assess whethdr the followng sLtatements are identocal in meuaning by answerinJ 'equivalent' or 'not_equivalent'. ", | |
| "transfer_ori_acc": 87.7, | |
| "transfer_atk_acc": 87.6 | |
| }, | |
| { | |
| "dataset": "qqp", | |
| "type": "role", | |
| "origin_acc": 82.5, | |
| "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": 79.5, | |
| "atk_prompt": "Ao 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. ", | |
| "transfer_ori_acc": 88.3, | |
| "transfer_atk_acc": 87.9 | |
| }, | |
| { | |
| "dataset": "rte", | |
| "type": "task", | |
| "origin_acc": 83.5, | |
| "origin_prompt": "Are the following two sentences entailment or not_entailment? Answer me with \"entailment\" or \"not_entailment\", just one word.", | |
| "atk_acc": 79.0, | |
| "atk_prompt": "ArYe the folowing two sentenes entailment or not_entailment? Answer me with \"entailment\" or \"not_entailment\", just one word. ", | |
| "transfer_ori_acc": 94.22382671480143, | |
| "transfer_atk_acc": 94.22382671480143 | |
| }, | |
| { | |
| "dataset": "rte", | |
| "type": "role", | |
| "origin_acc": 80.5, | |
| "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": 78.5, | |
| "atk_prompt": "IAs an instrument for entailment evaluatioRn, consider the otwo sentences and determine if their relationship is 'entailment' or 'not_entailment'. Respond with 'entailment' or 'not_entailment':", | |
| "transfer_ori_acc": 93.50180505415162, | |
| "transfer_atk_acc": 93.86281588447653 | |
| }, | |
| { | |
| "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": 88.5, | |
| "atk_prompt": "Deetrmine the overall sentLment of this sentence, categorizing it as 'positive' or 'negative': ", | |
| "transfer_ori_acc": 96.67431192660551, | |
| "transfer_atk_acc": 96.55963302752293 | |
| }, | |
| { | |
| "dataset": "sst2", | |
| "type": "role", | |
| "origin_acc": 93.0, | |
| "origin_prompt": "Functioning as a sentiment identification tool, assess if the following expression is 'positive' or 'negative'. Classify:", | |
| "atk_acc": 85.0, | |
| "atk_prompt": "uFnctioning as a sentmient identification tool, assess if the folGowing expression is 'positive' or 'negative'. Classify: ", | |
| "transfer_ori_acc": 95.9862385321101, | |
| "transfer_atk_acc": 95.52752293577981 | |
| }, | |
| { | |
| "dataset": "wnli", | |
| "type": "task", | |
| "origin_acc": 66.2, | |
| "origin_prompt": "Examine the pair of sentences and determine if they exhibit entailment or not_entailment. Answer with either 'entailment' or 'not_entailment'.", | |
| "atk_acc": 53.52, | |
| "atk_prompt": "Examine the Bair of snetences and determine if they exhibit entailment or not_entailment. Ancwer with eMther 'entailment' or 'not_entailment'.", | |
| "transfer_ori_acc": 78.87323943661971, | |
| "transfer_atk_acc": 77.46478873239437 | |
| }, | |
| { | |
| "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": 53.52, | |
| "atk_prompt": "IQn the role of a semantic relationship analyzer, eamine the connection between the given sentences and decide if they exhbit entailment or not_entailment. Answer with 'entailment' or 'not_entailment':", | |
| "transfer_ori_acc": 77.46478873239437, | |
| "transfer_atk_acc": 77.46478873239437 | |
| }, | |
| { | |
| "dataset": "mmlu", | |
| "type": "task", | |
| "origin_acc": 62.5, | |
| "origin_prompt": "Regarding the following multiple-choice question on {}, pick the correct answer from the options 'A', 'B', 'C', or 'D'.", | |
| "atk_acc": 60.0, | |
| "atk_prompt": "Regarding the following multiple-choice question on {}, pick the correct answeWr from the options 'A', 'B', 'C', or 'D'. ", | |
| "transfer_ori_acc": 52.304964539007095, | |
| "transfer_atk_acc": 52.4822695035461 | |
| }, | |
| { | |
| "dataset": "mmlu", | |
| "type": "role", | |
| "origin_acc": 62.5, | |
| "origin_prompt": "With your knowledge of {}, tackle the following multiple-choice question by choosing 'A', 'B', 'C', or 'D'.", | |
| "atk_acc": 59.0, | |
| "atk_prompt": "With your knowledge of {}, tackle the follQwing multiple-choice question by choosing 'A', 'B', 'C', or 'D'.", | |
| "transfer_ori_acc": 52.12765957446809, | |
| "transfer_atk_acc": 53.191489361702125 | |
| }, | |
| { | |
| "dataset": "squad_v2", | |
| "type": "task", | |
| "origin_acc": 71.87, | |
| "origin_prompt": "Discover the best answer based on the context. If the context doesn't include an answer, respond with 'unanswerable'.", | |
| "atk_acc": 56.61, | |
| "atk_prompt": "DiscoveMr the best answr bassd on the Rontext. Iof the cnotext doesn't include an answer, resCpond with 'unanswerable'.", | |
| "transfer_ori_acc": 89.38229949874687, | |
| "transfer_atk_acc": 90.38229949874687 | |
| }, | |
| { | |
| "dataset": "squad_v2", | |
| "type": "role", | |
| "origin_acc": 64.5, | |
| "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": 36.52, | |
| "atk_prompt": "zs an exprt with a deep understanding of the context, find the best answr. If the context doesn't include an anCswer, asy 'unanswerable'.", | |
| "transfer_ori_acc": 89.44479949874687, | |
| "transfer_atk_acc": 89.64896616541355 | |
| }, | |
| { | |
| "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 provideMd sentence from {} to {} while mainOaining the original meaning and context:", | |
| "transfer_ori_acc": 0.1697518407093131, | |
| "transfer_atk_acc": 0.1715931236169142 | |
| }, | |
| { | |
| "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 tanslator, plnase change the following senlence from {} to {}: ", | |
| "transfer_ori_acc": 0.17223574608131062, | |
| "transfer_atk_acc": 0.17294967708177186 | |
| }, | |
| { | |
| "dataset": "un_multi", | |
| "type": "task", | |
| "origin_acc": 0.34, | |
| "origin_prompt": "Translate the following text from the source language {} to the target language {}:", | |
| "atk_acc": 0.33, | |
| "atk_prompt": "Translate the following text from the source language {} to the Ptarget langugae {}:", | |
| "transfer_ori_acc": 0.30893486445367974, | |
| "transfer_atk_acc": 0.3118511970354398 | |
| }, | |
| { | |
| "dataset": "un_multi", | |
| "type": "role", | |
| "origin_acc": 0.34, | |
| "origin_prompt": "In the role of a language expert, perform a machine translation for the provided sentence, changing it from {} to {}:", | |
| "atk_acc": 0.32, | |
| "atk_prompt": "In the role of a language expert, pErform a macRhine yranslation for the provided sentence, cZanging it from {} to {}: ", | |
| "transfer_ori_acc": 0.31256243540663714, | |
| "transfer_atk_acc": 0.31148261863602605 | |
| }, | |
| { | |
| "dataset": "math", | |
| "type": "task", | |
| "origin_acc": 6.88, | |
| "origin_prompt": "Resolve the following mathematical question associated with {}:", | |
| "atk_acc": 5.62, | |
| "atk_prompt": "Resolve the following mathematical quXestion assocated with {}:", | |
| "transfer_ori_acc": 14.374999999999998, | |
| "transfer_atk_acc": 14.374999999999998 | |
| }, | |
| { | |
| "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, ind the anwer to the fpollowing math problem with {}: ", | |
| "transfer_ori_acc": 13.125, | |
| "transfer_atk_acc": 11.875 | |
| } | |
| ] |