Spaces:
Runtime error
Runtime error
| [ | |
| { | |
| "dataset": "cola", | |
| "type": "translation", | |
| "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": 84.6, | |
| "atk_prompt": "As a tool for assessing semantic relevance, categorize the sentence as 'acceptable' or 'unacceptable' according to its meaning and context.", | |
| "transfer_ori_acc": 74.6, | |
| "transfer_atk_acc": 76.4 | |
| }, | |
| { | |
| "dataset": "mrpc", | |
| "type": "translation", | |
| "origin_acc": 88.97, | |
| "origin_prompt": "As a sentence similarity evaluator, analyze the provided sentences and indicate if their meanings are 'equivalent' or 'not_equivalent'.", | |
| "atk_acc": 84.07, | |
| "atk_prompt": "Whether a given pair of sentences is 'equivalent' or 'not_equivalent' depends on the context.", | |
| "transfer_ori_acc": 79.16666666666666, | |
| "transfer_atk_acc": 80.63725490196079 | |
| }, | |
| { | |
| "dataset": "qnli", | |
| "type": "translation", | |
| "origin_acc": 94.5, | |
| "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": 83.0, | |
| "atk_prompt": "By analyzing the relations between sentences, determine if a given sentence does not necessarily include other sentences and answer with 'entailment' or 'not_entailment'.", | |
| "transfer_ori_acc": 89.60000000000001, | |
| "transfer_atk_acc": 86.6 | |
| }, | |
| { | |
| "dataset": "qqp", | |
| "type": "translation", | |
| "origin_acc": 90.0, | |
| "origin_prompt": "As a tool for determining question equivalence, review the questions and categorize their similarity as either 'equivalent' or 'not_equivalent'.", | |
| "atk_acc": 87.7, | |
| "atk_prompt": "Classify sentence equivalence as 'equivalent' or 'not_equivalent' by judging whether two sentences have the same meaning to each other.", | |
| "transfer_ori_acc": 86.3, | |
| "transfer_atk_acc": 85.39999999999999 | |
| }, | |
| { | |
| "dataset": "rte", | |
| "type": "translation", | |
| "origin_acc": 93.86, | |
| "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": 90.61, | |
| "atk_prompt": "Examine the semantic match of a given sentence and categorize it as 'entailment' or 'not_entailment'.", | |
| "transfer_ori_acc": 83.75451263537906, | |
| "transfer_atk_acc": 80.86642599277978 | |
| }, | |
| { | |
| "dataset": "sst2", | |
| "type": "translation", | |
| "origin_acc": 96.9, | |
| "origin_prompt": "Working as a sentiment analyzer, please indicate if the following text is 'positive' or 'negative'.", | |
| "atk_acc": 94.38, | |
| "atk_prompt": "As an emotion analysis tool, determine whether the emotion in the text is 'positive' or 'negative'.", | |
| "transfer_ori_acc": 95.29816513761467, | |
| "transfer_atk_acc": 93.34862385321101 | |
| }, | |
| { | |
| "dataset": "wnli", | |
| "type": "translation", | |
| "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": "For the purpose of determining implicative relations, analyze the relations of the following sentences and classify them as 'entailment' or 'not_entailment'.", | |
| "transfer_ori_acc": 64.7887323943662, | |
| "transfer_atk_acc": 57.74647887323944 | |
| }, | |
| { | |
| "dataset": "mmlu", | |
| "type": "translation", | |
| "origin_acc": 54.08, | |
| "origin_prompt": "For the multiple-choice question related to {}, please choose the most accurate answer from 'A', 'B', 'C', or 'D'.", | |
| "atk_acc": 51.95, | |
| "atk_prompt": "Choose the correct answer to the multiple-choice question below. Is '{}' an 'A', 'B', 'C', or 'D'.", | |
| "transfer_ori_acc": 45.56737588652482, | |
| "transfer_atk_acc": 45.21276595744681 | |
| }, | |
| { | |
| "dataset": "squad_v2", | |
| "type": "translation", | |
| "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": 88.73, | |
| "atk_prompt": "Consider the information derived from the given text and provide the most detailed answer. If the answer is not in the text, please answer 'unanswerable'.", | |
| "transfer_ori_acc": 87.01356406751144, | |
| "transfer_atk_acc": 86.91356406751143 | |
| }, | |
| { | |
| "dataset": "iwslt", | |
| "type": "translation", | |
| "origin_acc": 0.27, | |
| "origin_prompt": "Accurately translate the sentence from {} to {}, ensuring the meaning remains intact.", | |
| "atk_acc": 0.22, | |
| "atk_prompt": "Please translate the next sentence from {} to {}.", | |
| "transfer_ori_acc": 0.2195336520895316, | |
| "transfer_atk_acc": 0.21601471623392518 | |
| }, | |
| { | |
| "dataset": "un_multi", | |
| "type": "translation", | |
| "origin_acc": 0.36, | |
| "origin_prompt": "Perform a machine translation for the provided sentence, changing it from {} to {}.", | |
| "atk_acc": 0.35, | |
| "atk_prompt": "Please convert the following sentences to {} and translate to {}.", | |
| "transfer_ori_acc": 0.30870734220870066, | |
| "transfer_atk_acc": 0.30344234228764916 | |
| }, | |
| { | |
| "dataset": "math", | |
| "type": "translation", | |
| "origin_acc": 16.88, | |
| "origin_prompt": "Figure out the solution for the following mathematical task with {}.", | |
| "atk_acc": 10.0, | |
| "atk_prompt": "According to {}, set the following value.", | |
| "transfer_ori_acc": 17.5, | |
| "transfer_atk_acc": 15.625 | |
| } | |
| ] |