Spaces:
Runtime error
Runtime error
| [ | |
| { | |
| "dataset": "cola", | |
| "type": "task", | |
| "origin_acc": 86.4, | |
| "origin_prompt": "Review the sentence below and identify whether its grammar is 'Acceptable' or 'Unacceptable'.", | |
| "atk_acc": 83.6, | |
| "atk_prompt": "Reviee the sentence below and identfy wehther its grmamar is 'Acceptable' or 'Unacceptable'. ", | |
| "transfer_ori_acc": 76.7, | |
| "transfer_atk_acc": 75.8 | |
| }, | |
| { | |
| "dataset": "cola", | |
| "type": "role", | |
| "origin_acc": 86.9, | |
| "origin_prompt": "In the capacity of a grammar assessment system, indicate if the structure of the provided sentence is grammatically correct, responding with 'acceptable' or 'unacceptable'.", | |
| "atk_acc": 85.2, | |
| "atk_prompt": "Io the capcity of a grammar assessment system, indicate if the strcture of the povided senrence is grammatiaclly corrct, responding with 'acceptable' or 'unacceptable'. ", | |
| "transfer_ori_acc": 74.6, | |
| "transfer_atk_acc": 76.3 | |
| }, | |
| { | |
| "dataset": "mrpc", | |
| "type": "task", | |
| "origin_acc": 87.01, | |
| "origin_prompt": "Can the given sentences be considered semantically identical? Please reply with 'equivalent' or 'not_equivalent'.", | |
| "atk_acc": 84.31, | |
| "atk_prompt": "Can the given sentences be considered semantically idrntical? Please reply with 'equivalent' or 'not_equivalent'. ", | |
| "transfer_ori_acc": 82.35294117647058, | |
| "transfer_atk_acc": 80.14705882352942 | |
| }, | |
| { | |
| "dataset": "mrpc", | |
| "type": "role", | |
| "origin_acc": 87.5, | |
| "origin_prompt": "As a textual similarity evaluator, analyze the following pair of sentences and determine if they are semantically 'equivalent' or 'not_equivalent'.", | |
| "atk_acc": 84.56, | |
| "atk_prompt": "As a extual simialrity evaluator, analyze the following pair of sentences and determine if they are semantically 'equivalent' or 'not_equivalent'. ", | |
| "transfer_ori_acc": 79.41176470588235, | |
| "transfer_atk_acc": 80.88235294117648 | |
| }, | |
| { | |
| "dataset": "qnli", | |
| "type": "task", | |
| "origin_acc": 94.0, | |
| "origin_prompt": "Review the given context and question, and decide if the context contains enough information to support the answer by selecting 'entailment' or 'not_entailment'.", | |
| "atk_acc": 93.4, | |
| "atk_prompt": "Review the given cotext and question, and Pdecide if the context contains enough information to sGupport the answe by sefecting 'entailment' or 'not_entailment'. ", | |
| "transfer_ori_acc": 85.2, | |
| "transfer_atk_acc": 89.3 | |
| }, | |
| { | |
| "dataset": "qnli", | |
| "type": "role", | |
| "origin_acc": 93.7, | |
| "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": 92.9, | |
| "atk_prompt": "As a semantic interpreter, assless wether the provided context supports the answer to the given question and answer with 'entailment' or 'not_entailment'. ", | |
| "transfer_ori_acc": 88.0, | |
| "transfer_atk_acc": 79.60000000000001 | |
| }, | |
| { | |
| "dataset": "qqp", | |
| "type": "task", | |
| "origin_acc": 88.7, | |
| "origin_prompt": "Examine the following expressions and tell me if they are alike in meaning by using 'equivalent' or 'not_equivalent'.", | |
| "atk_acc": 87.4, | |
| "atk_prompt": "Examine the following expressiZns and tell me if they are aike in meaning by wusing 'equivalent' or 'not_equivalent'. ", | |
| "transfer_ori_acc": 86.7, | |
| "transfer_atk_acc": 86.9 | |
| }, | |
| { | |
| "dataset": "qqp", | |
| "type": "role", | |
| "origin_acc": 89.3, | |
| "origin_prompt": "While performing question comparison analysis, classify the similarity of the following questions as 'equivalent' for equivalent questions or 'not_equivalent' for different questions.", | |
| "atk_acc": 87.6, | |
| "atk_prompt": "While performing Pquestion comparison analysig, classify the simioarity of the following queFtions as 'equivalent' for equivalent questions or 'not_equivalent' for different questions. ", | |
| "transfer_ori_acc": 86.3, | |
| "transfer_atk_acc": 82.89999999999999 | |
| }, | |
| { | |
| "dataset": "rte", | |
| "type": "task", | |
| "origin_acc": 93.5, | |
| "origin_prompt": "Determine if the given pair of sentences displays entailment or not_entailment. Respond with 'entailment' or 'not_entailment'.", | |
| "atk_acc": 92.42, | |
| "atk_prompt": "Determine if the given paGr of sentenecs displays entailment or not_entailment. Respond with 'entailment' or 'not_entailment'. ", | |
| "transfer_ori_acc": 84.11552346570397, | |
| "transfer_atk_acc": 84.47653429602889 | |
| }, | |
| { | |
| "dataset": "rte", | |
| "type": "role", | |
| "origin_acc": 93.5, | |
| "origin_prompt": "As a tool for determining entailment relationships, review the two statements and categorize their connection as either 'entailment' or 'not_entailment'.", | |
| "atk_acc": 92.42, | |
| "atk_prompt": "AL a tool for determining entailment relationhsips, review the two staJements and categorize their connection as either 'entailment' or 'not_entailment'. ", | |
| "transfer_ori_acc": 83.39350180505414, | |
| "transfer_atk_acc": 83.03249097472924 | |
| }, | |
| { | |
| "dataset": "sst2", | |
| "type": "task", | |
| "origin_acc": 96.79, | |
| "origin_prompt": "Evaluate the sentiment of the given text and classify it as 'positive' or 'negative'.", | |
| "atk_acc": 96.33, | |
| "atk_prompt": "Evaluate the sentiment of the given tXxt and classify it as 'positive' or 'negative'. ", | |
| "transfer_ori_acc": 94.61009174311926, | |
| "transfer_atk_acc": 95.18348623853211 | |
| }, | |
| { | |
| "dataset": "sst2", | |
| "type": "role", | |
| "origin_acc": 96.56, | |
| "origin_prompt": "As a sentiment classifier, determine whether the following text is 'positive' or 'negative'.", | |
| "atk_acc": 96.1, | |
| "atk_prompt": "As a sentiment classifier, determine whether the followJing text is 'positive' or 'negative'. ", | |
| "transfer_ori_acc": 94.4954128440367, | |
| "transfer_atk_acc": 95.06880733944955 | |
| }, | |
| { | |
| "dataset": "wnli", | |
| "type": "task", | |
| "origin_acc": 77.46, | |
| "origin_prompt": "Assess the connection between the following sentences and classify it as 'entailment' or 'not_entailment'.", | |
| "atk_acc": 74.65, | |
| "atk_prompt": "Assuss the connection between the following sensences and classify it as 'entailment' or 'not_entailment'. ", | |
| "transfer_ori_acc": 64.7887323943662, | |
| "transfer_atk_acc": 66.19718309859155 | |
| }, | |
| { | |
| "dataset": "wnli", | |
| "type": "role", | |
| "origin_acc": 77.46, | |
| "origin_prompt": "Working as an entailment classifier, identify whether the given pair of sentences displays entailment or not_entailment. Respond with 'entailment' or 'not_entailment'.", | |
| "atk_acc": 76.06, | |
| "atk_prompt": "Working as an entailment classifeir, identify whether the given pair of sentences displays entailment or not_entailment. Respond with 'entailment' or 'not_entailment'. ", | |
| "transfer_ori_acc": 59.154929577464785, | |
| "transfer_atk_acc": 59.154929577464785 | |
| }, | |
| { | |
| "dataset": "mmlu", | |
| "type": "task", | |
| "origin_acc": 53.9, | |
| "origin_prompt": "Below are multiple-choice question concerning {}. Indicate your response with 'A', 'B', 'C', or 'D'.", | |
| "atk_acc": 52.3, | |
| "atk_prompt": "Belvw are multiple-chioce question conecrning {}. IndicaZe your response with 'A', 'B', 'C', or 'D'. ", | |
| "transfer_ori_acc": 45.39007092198582, | |
| "transfer_atk_acc": 45.21276595744681 | |
| }, | |
| { | |
| "dataset": "mmlu", | |
| "type": "role", | |
| "origin_acc": 54.08, | |
| "origin_prompt": "Considering your familiarity with {}, attend to the following multiple-choice question by picking 'A', 'B', 'C', or 'D'.", | |
| "atk_acc": 52.66, | |
| "atk_prompt": "Considering your familiarity with {}, atKtend to the follownig multipleNchoice juestion by picking 'A', 'B', 'C', or 'D'.", | |
| "transfer_ori_acc": 46.98581560283688, | |
| "transfer_atk_acc": 45.39007092198582 | |
| }, | |
| { | |
| "dataset": "squad_v2", | |
| "type": "task", | |
| "origin_acc": 91.05, | |
| "origin_prompt": "Identify the most relevant answer from the context. If it's not possible to find an answer, state 'unanswerable'.", | |
| "atk_acc": 89.38, | |
| "atk_prompt": "Identify the most rDlevant answer from the context. If it's not opssible to find an answer, tate 'unanswerable'.", | |
| "transfer_ori_acc": 87.01356406751144, | |
| "transfer_atk_acc": 87.14992770387508 | |
| }, | |
| { | |
| "dataset": "squad_v2", | |
| "type": "role", | |
| "origin_acc": 90.55, | |
| "origin_prompt": "Being well-versed in the context, please derive the most fitting answer. If there isn't an answer in the context, use 'unanswerable'.", | |
| "atk_acc": 89.32, | |
| "atk_prompt": "eBing well-versed in the contet, please drive the most fitting answer. If there isn't an answer in the context, Euse 'unanswerable'.", | |
| "transfer_ori_acc": 87.04992770387507, | |
| "transfer_atk_acc": 86.81659437054175 | |
| }, | |
| { | |
| "dataset": "iwslt", | |
| "type": "task", | |
| "origin_acc": 0.24, | |
| "origin_prompt": "Perform a machine translation for the provided sentence, changing it from {} to {}.", | |
| "atk_acc": 0.19, | |
| "atk_prompt": "Preform a machine translatino for the provied senteXce, chanigng it from {} to {}. ", | |
| "transfer_ori_acc": 0.21844565154870102, | |
| "transfer_atk_acc": 0.1826483660583944 | |
| }, | |
| { | |
| "dataset": "iwslt", | |
| "type": "role", | |
| "origin_acc": 0.27, | |
| "origin_prompt": "Taking on the role of a certified translator, perform a translation of the given sentence from {} to {}.", | |
| "atk_acc": 0.21, | |
| "atk_prompt": "Tking on the role of a Aertified tranolator, pefrorm a transAlation of the gUven sentence from {} to {}. ", | |
| "transfer_ori_acc": 0.21945913242821213, | |
| "transfer_atk_acc": 0.22244343277242712 | |
| }, | |
| { | |
| "dataset": "un_multi", | |
| "type": "task", | |
| "origin_acc": 0.36, | |
| "origin_prompt": "Perform a machine translation for the provided sentence, changing it from {} to {}.", | |
| "atk_acc": 0.35, | |
| "atk_prompt": "PeVform a machine transAation for the provide setence, changlng it from {} to {}. ", | |
| "transfer_ori_acc": 0.30870734220870066, | |
| "transfer_atk_acc": 0.3106194281548195 | |
| }, | |
| { | |
| "dataset": "un_multi", | |
| "type": "role", | |
| "origin_acc": 0.36, | |
| "origin_prompt": "As a skilled linguist, please convert the following sentence from {} to {}.", | |
| "atk_acc": 0.35, | |
| "atk_prompt": "AK a skilled linguist, please onvert the following sentence from {} to {}. ", | |
| "transfer_ori_acc": 0.3046140486156621, | |
| "transfer_atk_acc": 0.3111756468648709 | |
| }, | |
| { | |
| "dataset": "math", | |
| "type": "task", | |
| "origin_acc": 16.88, | |
| "origin_prompt": "Figure out the solution for the following mathematical task with {}.", | |
| "atk_acc": 14.37, | |
| "atk_prompt": "Figure out the solution for the following maKthematical Utask with {}. ", | |
| "transfer_ori_acc": 17.5, | |
| "transfer_atk_acc": 18.125 | |
| }, | |
| { | |
| "dataset": "math", | |
| "type": "role", | |
| "origin_acc": 16.88, | |
| "origin_prompt": "Pretend you are a math teacher and solve this mathematical question concerning {}.", | |
| "atk_acc": 15.0, | |
| "atk_prompt": "Petend you are a math teacher and solve this mathematical euestion concCerning {}. ", | |
| "transfer_ori_acc": 16.875, | |
| "transfer_atk_acc": 16.25 | |
| } | |
| ] |