Spaces:
Runtime error
Runtime error
| [ | |
| { | |
| "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": 6.0, | |
| "transfer_atk_acc": 1.0999999999999999 | |
| }, | |
| { | |
| "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": 49.9, | |
| "transfer_atk_acc": 40.0 | |
| }, | |
| { | |
| "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": 65.19607843137256, | |
| "transfer_atk_acc": 66.17647058823529 | |
| }, | |
| { | |
| "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": 67.8921568627451, | |
| "transfer_atk_acc": 69.6078431372549 | |
| }, | |
| { | |
| "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": 32.4, | |
| "transfer_atk_acc": 39.5 | |
| }, | |
| { | |
| "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": 34.4, | |
| "transfer_atk_acc": 24.099999999999998 | |
| }, | |
| { | |
| "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": 34.8, | |
| "transfer_atk_acc": 27.6 | |
| }, | |
| { | |
| "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": 35.3, | |
| "transfer_atk_acc": 31.1 | |
| }, | |
| { | |
| "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": 49.81949458483754, | |
| "transfer_atk_acc": 46.931407942238266 | |
| }, | |
| { | |
| "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": 4.332129963898916, | |
| "transfer_atk_acc": 31.046931407942242 | |
| }, | |
| { | |
| "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": 1.7201834862385321, | |
| "transfer_atk_acc": 5.275229357798166 | |
| }, | |
| { | |
| "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": 10.77981651376147, | |
| "transfer_atk_acc": 25.0 | |
| }, | |
| { | |
| "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": 19.718309859154928, | |
| "transfer_atk_acc": 15.492957746478872 | |
| }, | |
| { | |
| "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": 9.859154929577464, | |
| "transfer_atk_acc": 4.225352112676056 | |
| }, | |
| { | |
| "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": 9.397163120567376, | |
| "transfer_atk_acc": 9.397163120567376 | |
| }, | |
| { | |
| "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": 8.156028368794328, | |
| "transfer_atk_acc": 9.397163120567376 | |
| } | |
| ] |