Spaces:
Runtime error
Runtime error
| [ | |
| { | |
| "dataset": "cola", | |
| "type": "translation", | |
| "origin_acc": 78.0, | |
| "origin_prompt": "Assess the following sentence and determine if it is grammatically correct. Respond with 'Acceptable' or 'Unacceptable':", | |
| "atk_acc": 74.6, | |
| "atk_prompt": "As a tool for classifying valid sentences, determine whether 'acceptable' or 'unacceptable' is based on its grammatical rules.", | |
| "transfer_ori_acc": 86.2, | |
| "transfer_atk_acc": 85.8 | |
| }, | |
| { | |
| "dataset": "mrpc", | |
| "type": "translation", | |
| "origin_acc": 82.6, | |
| "origin_prompt": "As a semantic comparison expert, evaluate the given pair of sentences and determine if they are 'equivalent' or 'not_equivalent'.", | |
| "atk_acc": 77.7, | |
| "atk_prompt": "Determine whether a given pair of sentences is 'equivalent' or 'not_equivalent', and whether they are semantically identical.", | |
| "transfer_ori_acc": 84.31372549019608, | |
| "transfer_atk_acc": 85.29411764705883 | |
| }, | |
| { | |
| "dataset": "qnli", | |
| "type": "translation", | |
| "origin_acc": 89.8, | |
| "origin_prompt": "Evaluate whether the given context supports the answer to the question by responding with 'entailment' or 'not_entailment'.", | |
| "atk_acc": 53.1, | |
| "atk_prompt": "Answer with 'entailment' or 'not_entailment', inferring from the given context.", | |
| "transfer_ori_acc": 93.89999999999999, | |
| "transfer_atk_acc": 93.4 | |
| }, | |
| { | |
| "dataset": "qqp", | |
| "type": "translation", | |
| "origin_acc": 88.1, | |
| "origin_prompt": "Are the following two questions equivalent or not? Answer me with \"equivalent\" or \"not_equivalent\".", | |
| "atk_acc": 70.9, | |
| "atk_prompt": "As a tool for determining the equivalence of problems, the problems are examined and their similarity is classified as 'equivalent' or 'not_equivalent'.", | |
| "transfer_ori_acc": 87.8, | |
| "transfer_atk_acc": 87.3 | |
| }, | |
| { | |
| "dataset": "rte", | |
| "type": "translation", | |
| "origin_acc": 86.64, | |
| "origin_prompt": "Are the following two sentences entailment or not_entailment? Answer me with \"entailment\" or \"not_entailment\", just one word.", | |
| "atk_acc": 80.51, | |
| "atk_prompt": "Determinate the semantic connections of a given sentence and classify it as 'entailment' or 'not_entailment'.", | |
| "transfer_ori_acc": 94.22382671480143, | |
| "transfer_atk_acc": 90.97472924187726 | |
| }, | |
| { | |
| "dataset": "sst2", | |
| "type": "translation", | |
| "origin_acc": 95.41, | |
| "origin_prompt": "In the role of a sentiment analysis tool, respond with 'positive' or 'negative' to classify this statement:", | |
| "atk_acc": 92.78, | |
| "atk_prompt": "Classify what you're trying to convey in this sentence as 'positive' if it's positive, and 'negative' if it's negative.", | |
| "transfer_ori_acc": 96.44495412844036, | |
| "transfer_atk_acc": 96.55963302752293 | |
| }, | |
| { | |
| "dataset": "wnli", | |
| "type": "translation", | |
| "origin_acc": 66.2, | |
| "origin_prompt": "Are the following two sentences entailment or not_entailment? Answer me with \"entailment\" or \"not_entailment\", just one word.", | |
| "atk_acc": 49.3, | |
| "atk_prompt": "Examine the paraphrases of a given sentence and classify them 'entailment' or 'not_entailment'.", | |
| "transfer_ori_acc": 78.87323943661971, | |
| "transfer_atk_acc": 78.87323943661971 | |
| }, | |
| { | |
| "dataset": "mmlu", | |
| "type": "translation", | |
| "origin_acc": 45.74, | |
| "origin_prompt": "For each multiple-choice question about {}, identify the correct answer by selecting 'A', 'B', 'C', or 'D'.", | |
| "atk_acc": 41.84, | |
| "atk_prompt": "Choose the correct answer for '{}' from 'A', 'B', 'C', or 'D' in the multiple choice problem involving,", | |
| "transfer_ori_acc": 51.77304964539007, | |
| "transfer_atk_acc": 53.90070921985816 | |
| }, | |
| { | |
| "dataset": "squad_v2", | |
| "type": "translation", | |
| "origin_acc": 88.18, | |
| "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": 84.51, | |
| "atk_prompt": "Please give the cause of the incident mentioned in the context. If the cause is not clear, respond with 'unanswerable'.", | |
| "transfer_ori_acc": 89.88229949874687, | |
| "transfer_atk_acc": 88.87093586238325 | |
| }, | |
| { | |
| "dataset": "iwslt", | |
| "type": "translation", | |
| "origin_acc": 0.14, | |
| "origin_prompt": "Please perform a translation of the given sentence, converting it from {} to {}:", | |
| "atk_acc": 0.12, | |
| "atk_prompt": "Please translate the sentences below into {}, then {}.", | |
| "transfer_ori_acc": 0.17287994792239936, | |
| "transfer_atk_acc": 0.1731981736461422 | |
| }, | |
| { | |
| "dataset": "un_multi", | |
| "type": "translation", | |
| "origin_acc": 0.27, | |
| "origin_prompt": "Convert the following sentence from its original {} language to the target language {}:", | |
| "atk_acc": 0.26, | |
| "atk_prompt": "Please translate the next sentence from {} to {}.", | |
| "transfer_ori_acc": 0.31092395135800066, | |
| "transfer_atk_acc": 0.3173709801911563 | |
| }, | |
| { | |
| "dataset": "math", | |
| "type": "translation", | |
| "origin_acc": 16.25, | |
| "origin_prompt": "Evaluate the following mathematical problem that includes {}:", | |
| "atk_acc": 10.62, | |
| "atk_prompt": "Compute the result of {}.", | |
| "transfer_ori_acc": 13.750000000000002, | |
| "transfer_atk_acc": 12.5 | |
| } | |
| ] |