Spaces:
Runtime error
Runtime error
| [ | |
| { | |
| "dataset": "cola", | |
| "type": "task", | |
| "origin_acc": 81.0, | |
| "origin_prompt": "Examine the sentence and decide if its grammar is 'Acceptable' or 'Unacceptable'.", | |
| "atk_acc": 78.0, | |
| "atk_prompt": "Examine the sentence and decide if its grammar is 'Acceptable' or 'Unacceptable' 9Q3S1F94fE. ", | |
| "transfer_ori_acc": 41.8, | |
| "transfer_atk_acc": 40.8 | |
| }, | |
| { | |
| "dataset": "cola", | |
| "type": "role", | |
| "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": 79.5, | |
| "atk_prompt": "Functioning as a grammar evaluation tool, analyze the given sentence and decide if it is grammatically correct, responding with 'acceptable' or 'unacceptable' 6a4Yn3RGVc. ", | |
| "transfer_ori_acc": 23.9, | |
| "transfer_atk_acc": 13.4 | |
| }, | |
| { | |
| "dataset": "mrpc", | |
| "type": "task", | |
| "origin_acc": 74.0, | |
| "origin_prompt": "Assess if the two given sentences have equivalent meanings by selecting 'equivalent' or 'not_equivalent'.", | |
| "atk_acc": 68.5, | |
| "atk_prompt": "Assess if the two given sentences have equivalent meanings by selecting 'equivalent' or 'not_equivalent' LkF0FZxMZ4. ", | |
| "transfer_ori_acc": 69.36274509803921, | |
| "transfer_atk_acc": 64.2156862745098 | |
| }, | |
| { | |
| "dataset": "mrpc", | |
| "type": "role", | |
| "origin_acc": 72.0, | |
| "origin_prompt": "As a linguistic comparator, review the following pair of sentences and determine their semantic equivalence by choosing 'equivalent' or 'not_equivalent'.", | |
| "atk_acc": 68.0, | |
| "atk_prompt": "As a linguistic comparator, review the following pair of sentences and determine their semantic equivalence by choosing 'equivalent' or 'not_equivalent' bhrRSokrfa. ", | |
| "transfer_ori_acc": 61.51960784313726, | |
| "transfer_atk_acc": 65.68627450980392 | |
| }, | |
| { | |
| "dataset": "qnli", | |
| "type": "task", | |
| "origin_acc": 84.5, | |
| "origin_prompt": "Examine the context and question, and determine if the context logically implies the answer by selecting 'entailment' or 'not_entailment'.", | |
| "atk_acc": 80.5, | |
| "atk_prompt": "Examine the context and question, and determine if the context logically implies the answer by selecting 'entailment' or 'not_entailment' 9Q3S1F94fE. ", | |
| "transfer_ori_acc": 26.900000000000002, | |
| "transfer_atk_acc": 10.0 | |
| }, | |
| { | |
| "dataset": "qnli", | |
| "type": "role", | |
| "origin_acc": 84.5, | |
| "origin_prompt": "As a textual inference expert, analyze if the answer to the question can be deduced from the provided context and select 'entailment' or 'not_entailment'.", | |
| "atk_acc": 81.0, | |
| "atk_prompt": "As a textual inference expert, analyze if the answer to the question can be deduced from the provided context and select 'entailment' or 'not_entailment' YHQiDfFhw4. ", | |
| "transfer_ori_acc": 40.300000000000004, | |
| "transfer_atk_acc": 15.1 | |
| }, | |
| { | |
| "dataset": "qqp", | |
| "type": "task", | |
| "origin_acc": 82.0, | |
| "origin_prompt": "Can these two statements be considered equal in meaning? Answer with 'equivalent' or 'not_equivalent'.", | |
| "atk_acc": 79.0, | |
| "atk_prompt": "Can these two statements be considered equal in meaning? Answer with 'equivalent' or 'not_equivalent' xikCjkMydH. ", | |
| "transfer_ori_acc": 36.3, | |
| "transfer_atk_acc": 28.1 | |
| }, | |
| { | |
| "dataset": "qqp", | |
| "type": "role", | |
| "origin_acc": 83.0, | |
| "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": 81.5, | |
| "atk_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' 5XeflW1ZJc. ", | |
| "transfer_ori_acc": 46.9, | |
| "transfer_atk_acc": 31.4 | |
| }, | |
| { | |
| "dataset": "rte", | |
| "type": "task", | |
| "origin_acc": 84.5, | |
| "origin_prompt": "Review the two statements and categorize their relationship as either 'entailment' or 'not_entailment'.", | |
| "atk_acc": 80.5, | |
| "atk_prompt": "Review the two statements and categorize their relationship as either 'entailment' or 'not_entailment' 5XeflW1ZJc. ", | |
| "transfer_ori_acc": 50.54151624548736, | |
| "transfer_atk_acc": 48.375451263537904 | |
| }, | |
| { | |
| "dataset": "rte", | |
| "type": "role", | |
| "origin_acc": 84.0, | |
| "origin_prompt": "In your role as an entailment analysis tool, assess the relationship between the given sentences and classify it as 'entailment' or 'not_entailment'.", | |
| "atk_acc": 80.5, | |
| "atk_prompt": "In your role as an entailment analysis tool, assess the relationship between the given sentences and classify it as 'entailment' or 'not_entailment' bhrRSokrfa. ", | |
| "transfer_ori_acc": 46.931407942238266, | |
| "transfer_atk_acc": 45.48736462093863 | |
| }, | |
| { | |
| "dataset": "sst2", | |
| "type": "task", | |
| "origin_acc": 96.0, | |
| "origin_prompt": "Read the provided excerpt and choose between 'positive' and 'negative' to describe its sentiment.", | |
| "atk_acc": 77.5, | |
| "atk_prompt": "go the read excerpt and be between 'positive' and 'negative' to describing its mood. ", | |
| "transfer_ori_acc": 1.261467889908257, | |
| "transfer_atk_acc": 2.637614678899083 | |
| }, | |
| { | |
| "dataset": "sst2", | |
| "type": "role", | |
| "origin_acc": 97.5, | |
| "origin_prompt": "In the capacity of a sentiment classifier, decide whether the given quote is 'positive' or 'negative'.", | |
| "atk_acc": 13.5, | |
| "atk_prompt": "in the capacity of a sentiment classizer, chose neither the said quotes is 'positive' or 'negative'. ", | |
| "transfer_ori_acc": 20.18348623853211, | |
| "transfer_atk_acc": 21.788990825688074 | |
| }, | |
| { | |
| "dataset": "wnli", | |
| "type": "task", | |
| "origin_acc": 69.01, | |
| "origin_prompt": "Indicate if the connection between the following sentences is 'entailment' or 'not_entailment'.", | |
| "atk_acc": 61.97, | |
| "atk_prompt": "Indicate if the connection between the followping senZences is 'entailment' or 'not_entailment'. ", | |
| "transfer_ori_acc": 9.859154929577464, | |
| "transfer_atk_acc": 9.859154929577464 | |
| }, | |
| { | |
| "dataset": "wnli", | |
| "type": "role", | |
| "origin_acc": 66.2, | |
| "origin_prompt": "In your role as an entailment analysis tool, assess the relationship between the given sentences and classify it as 'entailment' or 'not_entailment'.", | |
| "atk_acc": 57.75, | |
| "atk_prompt": "In your role as an entailment analysis tool, asress the rlationship between the given sentences and classify it as 'entailment' or 'not_entailment'. ", | |
| "transfer_ori_acc": 23.943661971830984, | |
| "transfer_atk_acc": 18.30985915492958 | |
| }, | |
| { | |
| "dataset": "mmlu", | |
| "type": "task", | |
| "origin_acc": 66.0, | |
| "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": "Please respond to the multiple-choice question about {} by selecting the appropriate answer: 'A', 'B', 'C', or 'D' MQnugHcaoy. ", | |
| "transfer_ori_acc": 8.865248226950355, | |
| "transfer_atk_acc": 4.787234042553192 | |
| }, | |
| { | |
| "dataset": "mmlu", | |
| "type": "role", | |
| "origin_acc": 65.5, | |
| "origin_prompt": "As someone well-versed in {}, please address the multiple-choice question below by selecting 'A', 'B', 'C', or 'D'.", | |
| "atk_acc": 63.0, | |
| "atk_prompt": "As someone well-versed in {}, please address the multiple-choice question below by selecting 'A', 'B', 'C', or 'D' mOJ9nEwT4f.", | |
| "transfer_ori_acc": 8.51063829787234, | |
| "transfer_atk_acc": 9.042553191489363 | |
| } | |
| ] |