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": 75.5, | |
| "atk_prompt": "Is the provided sentence grammatically correct? Respond with 'Acceptable' or 'Unacceptable' and false is not true . ", | |
| "transfer_ori_acc": 86.6, | |
| "transfer_atk_acc": 86.3 | |
| }, | |
| { | |
| "dataset": "cola", | |
| "type": "role", | |
| "origin_acc": 75.8, | |
| "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": 75.2, | |
| "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 and false is not true . ", | |
| "transfer_ori_acc": 86.0, | |
| "transfer_atk_acc": 86.2 | |
| }, | |
| { | |
| "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": 24.51, | |
| "atk_prompt": "Evaluate whether the two provided sentences convey the same meaning by answering 'equivalent' or 'not_equivalent' and true is true and true is true and true is true and true is true and true is true . ", | |
| "transfer_ori_acc": 85.7843137254902, | |
| "transfer_atk_acc": 86.02941176470588 | |
| }, | |
| { | |
| "dataset": "mrpc", | |
| "type": "role", | |
| "origin_acc": 80.15, | |
| "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": 17.4, | |
| "atk_prompt": "As a language comparison expert, examine the given pair of sentences and decide if their meanings align, answering with 'equivalent' or 'not_equivalent' and true is true and true is true and true is true and true is true and true is true . ", | |
| "transfer_ori_acc": 86.51960784313727, | |
| "transfer_atk_acc": 85.5392156862745 | |
| }, | |
| { | |
| "dataset": "qnli", | |
| "type": "task", | |
| "origin_acc": 87.8, | |
| "origin_prompt": "Based on the information in the context, decide if the answer to the question is justified by choosing 'entailment' or 'not_entailment'.", | |
| "atk_acc": 79.4, | |
| "atk_prompt": "Based on the information in the context, decide if the answer to the question is justified by choosing 'entailment' or 'not_entailment' and true is true and true is true and true is true and true is true and true is true . ", | |
| "transfer_ori_acc": 93.8, | |
| "transfer_atk_acc": 94.39999999999999 | |
| }, | |
| { | |
| "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": 68.9, | |
| "atk_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' and true is true and true is true and true is true and true is true and true is true . ", | |
| "transfer_ori_acc": 93.60000000000001, | |
| "transfer_atk_acc": 94.1 | |
| }, | |
| { | |
| "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": 23.4, | |
| "atk_prompt": "Are the following two questions equivalent or not? Answer me with \"equivalent\" or \"not_equivalent and false is not true \". ", | |
| "transfer_ori_acc": 88.5, | |
| "transfer_atk_acc": 88.4 | |
| }, | |
| { | |
| "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": 86.4, | |
| "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 and true is true . ", | |
| "transfer_ori_acc": 89.0, | |
| "transfer_atk_acc": 88.6 | |
| }, | |
| { | |
| "dataset": "rte", | |
| "type": "task", | |
| "origin_acc": 84.84, | |
| "origin_prompt": "Identify whether the given pair of sentences demonstrates entailment or not_entailment. Answer with 'entailment' or 'not_entailment'.", | |
| "atk_acc": 43.68, | |
| "atk_prompt": "Identify whether the given pair of sentences demonstrates entailment or not_entailment. Answer with 'entailment' or 'not_entailment' and true is true and true is true and true is true and true is true and true is true . ", | |
| "transfer_ori_acc": 93.14079422382672, | |
| "transfer_atk_acc": 93.14079422382672 | |
| }, | |
| { | |
| "dataset": "rte", | |
| "type": "role", | |
| "origin_acc": 84.12, | |
| "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": 36.82, | |
| "atk_prompt": "In the capacity of an entailment assessment system, indicate if the link between the following sentences is 'entailment' or 'not_entailment' and true is true and true is true and true is true and true is true and true is true . ", | |
| "transfer_ori_acc": 92.4187725631769, | |
| "transfer_atk_acc": 92.4187725631769 | |
| }, | |
| { | |
| "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": 94.61, | |
| "atk_prompt": "Considering the given phrase, would you say it carries a 'positive' or 'negative' connotation and false is not true ? ", | |
| "transfer_ori_acc": 95.64220183486239, | |
| "transfer_atk_acc": 95.9862385321101 | |
| }, | |
| { | |
| "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": 95.07, | |
| "atk_prompt": "Acting as a sentiment evaluator, identify if the given sentence is 'positive' or 'negative' and true is true . ", | |
| "transfer_ori_acc": 96.55963302752293, | |
| "transfer_atk_acc": 96.44495412844036 | |
| }, | |
| { | |
| "dataset": "wnli", | |
| "type": "task", | |
| "origin_acc": 66.2, | |
| "origin_prompt": "Analyze the two provided sentences and decide if their relationship is 'entailment' or 'not_entailment'.", | |
| "atk_acc": 35.21, | |
| "atk_prompt": "Analyze the two provided sentences and decide if their relationship is 'entailment' or 'not_entailment' and true is true and true is true and true is true and true is true and true is true . ", | |
| "transfer_ori_acc": 77.46478873239437, | |
| "transfer_atk_acc": 76.05633802816901 | |
| }, | |
| { | |
| "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": 23.94, | |
| "atk_prompt": "In the capacity of an entailment assessment system, indicate if the link between the following sentences is 'entailment' or 'not_entailment' and true is true and true is true and true is true and true is true and true is true . ", | |
| "transfer_ori_acc": 76.05633802816901, | |
| "transfer_atk_acc": 73.23943661971832 | |
| }, | |
| { | |
| "dataset": "mmlu", | |
| "type": "task", | |
| "origin_acc": 45.92, | |
| "origin_prompt": "Answer the subsequent multiple-choice question about {} by picking the right option among 'A', 'B', 'C', or 'D'.", | |
| "atk_acc": 44.86, | |
| "atk_prompt": "Answer the subsequent multiple-choice question about {} by picking the right option among 'A', 'B', 'C', or 'D' and false is not true . ", | |
| "transfer_ori_acc": 53.72340425531915, | |
| "transfer_atk_acc": 52.12765957446809 | |
| }, | |
| { | |
| "dataset": "mmlu", | |
| "type": "role", | |
| "origin_acc": 46.63, | |
| "origin_prompt": "As someone well-versed in {}, please address the multiple-choice question below by selecting 'A', 'B', 'C', or 'D'.", | |
| "atk_acc": 44.86, | |
| "atk_prompt": "As someone well-versed in {}, please address the multiple-choice question below by selecting 'A', 'B', 'C', or 'D' and false is not true .", | |
| "transfer_ori_acc": 53.01418439716312, | |
| "transfer_atk_acc": 51.95035460992907 | |
| }, | |
| { | |
| "dataset": "squad_v2", | |
| "type": "task", | |
| "origin_acc": 87.91, | |
| "origin_prompt": "From the context, provide the most precise answer. If the answer is not in the context, respond with 'unanswerable'.", | |
| "atk_acc": 87.05, | |
| "atk_prompt": "From the context, provide the most precise answer. If the answer is not in the context, respond with 'unanswerable' and true is true and true is true and true is true and true is true and true is true .", | |
| "transfer_ori_acc": 89.38229949874687, | |
| "transfer_atk_acc": 89.88229949874687 | |
| }, | |
| { | |
| "dataset": "squad_v2", | |
| "type": "role", | |
| "origin_acc": 87.32, | |
| "origin_prompt": "As a proficient expert in the given context, search for the most relevant answer. If the answer cannot be found, respond by saying 'unanswerable'.", | |
| "atk_acc": 86.65, | |
| "atk_prompt": "As a proficient expert in the given context, search for the most relevant answer. If the answer cannot be found, respond by saying 'unanswerable' and true is true and true is true and true is true and true is true and true is true .", | |
| "transfer_ori_acc": 90.54896616541353, | |
| "transfer_atk_acc": 90.54896616541353 | |
| }, | |
| { | |
| "dataset": "iwslt", | |
| "type": "task", | |
| "origin_acc": 0.22, | |
| "origin_prompt": "Convert the following sentence from its original {} language to the target language {}.", | |
| "atk_acc": 0.22, | |
| "atk_prompt": "Convert the following sentence from its original {} language to the target language and true is true {}. ", | |
| "transfer_ori_acc": 0.23981220411098694, | |
| "transfer_atk_acc": 0.19706994450619086 | |
| }, | |
| { | |
| "dataset": "iwslt", | |
| "type": "role", | |
| "origin_acc": 0.22, | |
| "origin_prompt": "In the role of a language expert, perform a machine translation for the provided sentence, changing it from {} to {}.", | |
| "atk_acc": 0.21, | |
| "atk_prompt": "In the role of a language expert, perform a machine translation for the provided sentence, changing it from {} to and false is not true {}. ", | |
| "transfer_ori_acc": 0.236844571841243, | |
| "transfer_atk_acc": 0.23378656190205807 | |
| }, | |
| { | |
| "dataset": "un_multi", | |
| "type": "task", | |
| "origin_acc": 0.31, | |
| "origin_prompt": "Translate the following text from the source language {} to the target language {}.", | |
| "atk_acc": 0.3, | |
| "atk_prompt": "Translate the following text from the source language {} to the target language and false is not true {}. ", | |
| "transfer_ori_acc": 0.35343571054545636, | |
| "transfer_atk_acc": 0.3526627578400292 | |
| }, | |
| { | |
| "dataset": "un_multi", | |
| "type": "role", | |
| "origin_acc": 0.31, | |
| "origin_prompt": "Taking on the role of a certified translator, perform a translation of the given sentence from {} to {}.", | |
| "atk_acc": 0.3, | |
| "atk_prompt": "Taking on the role of a certified translator, perform a translation of the given sentence from {} to and true is true and true is true and true is true and true is true and true is true {}. ", | |
| "transfer_ori_acc": 0.35510202593913104, | |
| "transfer_atk_acc": 0.3486065615860692 | |
| }, | |
| { | |
| "dataset": "math", | |
| "type": "task", | |
| "origin_acc": 17.5, | |
| "origin_prompt": "Find the solution for this mathematical challenge with {}.", | |
| "atk_acc": 16.25, | |
| "atk_prompt": "Find the solution for this mathematical challenge with and false is not true {}. ", | |
| "transfer_ori_acc": 15.625, | |
| "transfer_atk_acc": 13.750000000000002 | |
| }, | |
| { | |
| "dataset": "math", | |
| "type": "role", | |
| "origin_acc": 18.12, | |
| "origin_prompt": "Embodying a mathematics advisor, find the answer to the following math problem with {}.", | |
| "atk_acc": 16.25, | |
| "atk_prompt": "Embodying a mathematics advisor, find the answer to the following math problem with and false is not true {}. ", | |
| "transfer_ori_acc": 15.0, | |
| "transfer_atk_acc": 11.875 | |
| } | |
| ] |