Spaces:
Runtime error
Runtime error
| [ | |
| { | |
| "dataset": "cola", | |
| "type": "translation", | |
| "origin_acc": 81.5, | |
| "origin_prompt": "Functioning as a grammar evaluation tool, analyze the given sentence and decide if it is grammatically correct, responding with 'acceptable' or 'unacceptable'.", | |
| "atk_acc": 68.5, | |
| "atk_prompt": "Classify the grammar of a given sentence as 'acceptable' or 'unacceptable', and judge its accuracy.", | |
| "transfer_ori_acc": 86.4, | |
| "transfer_atk_acc": 86.0 | |
| }, | |
| { | |
| "dataset": "mrpc", | |
| "type": "translation", | |
| "origin_acc": 74.5, | |
| "origin_prompt": "Compare the following sentences and determine if they share the same semantic meaning by responding with 'equivalent' or 'not_equivalent'.", | |
| "atk_acc": 65.0, | |
| "atk_prompt": "Based on my experience in semantic analysis, classify the following two sentences between 'equivalent' or 'not_equivalent'.", | |
| "transfer_ori_acc": 86.27450980392157, | |
| "transfer_atk_acc": 85.04901960784314 | |
| }, | |
| { | |
| "dataset": "qnli", | |
| "type": "translation", | |
| "origin_acc": 86.0, | |
| "origin_prompt": "As a textual analyst, examine if the given context logically implies the answer to the question and indicate your decision with 'entailment' or 'not_entailment'.", | |
| "atk_acc": 71.5, | |
| "atk_prompt": "Check the text link to the question and answer 'entailment' or 'not_entailment', depending on your language skills.", | |
| "transfer_ori_acc": 93.2, | |
| "transfer_atk_acc": 93.0 | |
| }, | |
| { | |
| "dataset": "qqp", | |
| "type": "translation", | |
| "origin_acc": 84.0, | |
| "origin_prompt": "In the capacity of a question assessment system, indicate if the meaning of the provided questions is the same, responding with 'equivalent' or 'not_equivalent'.", | |
| "atk_acc": 80.5, | |
| "atk_prompt": "By analyzing the similarity of these problems, they are divided into categories of 'equivalent' or 'not_equivalent'.", | |
| "transfer_ori_acc": 88.7, | |
| "transfer_atk_acc": 89.60000000000001 | |
| }, | |
| { | |
| "dataset": "rte", | |
| "type": "translation", | |
| "origin_acc": 84.5, | |
| "origin_prompt": "Does the relationship between the given sentences represent entailment or not_entailment? Respond with 'entailment' or 'not_entailment'.", | |
| "atk_acc": 80.0, | |
| "atk_prompt": "Determine whether the given sentences have a cause-effect relationship as an engagement analysis tool and categorize them as 'entailment' or 'not_entailment'.", | |
| "transfer_ori_acc": 93.86281588447653, | |
| "transfer_atk_acc": 92.4187725631769 | |
| }, | |
| { | |
| "dataset": "sst2", | |
| "type": "translation", | |
| "origin_acc": 97.5, | |
| "origin_prompt": "In the capacity of a sentiment classifier, decide whether the given quote is 'positive' or 'negative'.", | |
| "atk_acc": 68.5, | |
| "atk_prompt": "In the context of textual analysis, what classification is this phrase between 'positive' and 'negative'?", | |
| "transfer_ori_acc": 96.44495412844036, | |
| "transfer_atk_acc": 96.78899082568807 | |
| }, | |
| { | |
| "dataset": "wnli", | |
| "type": "translation", | |
| "origin_acc": 74.65, | |
| "origin_prompt": "Are the following two sentences entailment or not_entailment? Answer me with \"entailment\" or \"not_entailment\", just one word.", | |
| "atk_acc": 59.15, | |
| "atk_prompt": "Determinate the semantic connections of a given sentence and classify it as 'entailment' or 'not_entailment'.", | |
| "transfer_ori_acc": 76.05633802816901, | |
| "transfer_atk_acc": 76.05633802816901 | |
| }, | |
| { | |
| "dataset": "mmlu", | |
| "type": "translation", | |
| "origin_acc": 67.0, | |
| "origin_prompt": "Please respond to the multiple-choice question about {} by selecting the appropriate answer: 'A', 'B', 'C', or 'D'.", | |
| "atk_acc": 63.0, | |
| "atk_prompt": "Rate your understanding of the multiple-choice question on {}. Choose the correct answer from options 'A', 'B', 'C' or 'D'.", | |
| "transfer_ori_acc": 53.36879432624113, | |
| "transfer_atk_acc": 53.72340425531915 | |
| }, | |
| { | |
| "dataset": "squad_v2", | |
| "type": "translation", | |
| "origin_acc": 74.58, | |
| "origin_prompt": "Please derive the most fitting answer from the context. If there isn't an answer in the context, use 'unanswerable'.", | |
| "atk_acc": 67.46, | |
| "atk_prompt": "Please provide additional information about the facts mentioned in this sentence. If no information is available, respond with 'unanswerable'.", | |
| "transfer_ori_acc": 90.54896616541353, | |
| "transfer_atk_acc": 90.88229949874687 | |
| }, | |
| { | |
| "dataset": "iwslt", | |
| "type": "translation", | |
| "origin_acc": 0.24, | |
| "origin_prompt": "Convert the following sentence from its original {} language to the target language {}.", | |
| "atk_acc": 0.17, | |
| "atk_prompt": "Please translate the sentences below into {}, then {}.", | |
| "transfer_ori_acc": 0.23981220411098694, | |
| "transfer_atk_acc": 0.23367230863817542 | |
| }, | |
| { | |
| "dataset": "un_multi", | |
| "type": "translation", | |
| "origin_acc": 0.36, | |
| "origin_prompt": "Translate the following text from the source language {} to the target language {}.", | |
| "atk_acc": 0.25, | |
| "atk_prompt": "Please translate the following sentences into {}, then {}.", | |
| "transfer_ori_acc": 0.35343571054545636, | |
| "transfer_atk_acc": 0.3537894516935946 | |
| }, | |
| { | |
| "dataset": "math", | |
| "type": "translation", | |
| "origin_acc": 23.12, | |
| "origin_prompt": "Compute the result of this math task concerning {}.", | |
| "atk_acc": 18.75, | |
| "atk_prompt": "Please calculate the answers related to {}.", | |
| "transfer_ori_acc": 16.25, | |
| "transfer_atk_acc": 16.875 | |
| } | |
| ] |