Spaces:
Runtime error
Runtime error
| [ | |
| { | |
| "dataset": "cola", | |
| "type": "task", | |
| "origin_acc": 78.1, | |
| "origin_prompt": "Assess the following sentence and determine if it is grammatically correct. Respond with 'Acceptable' or 'Unacceptable'.", | |
| "atk_acc": 77.0, | |
| "atk_prompt": "Assess the following sentence and determine if it is grammatically correct. Respond with 'Acceptable' or 'Unacceptable' zexKUTWJYG. ", | |
| "transfer_ori_acc": 0.8999999999999999, | |
| "transfer_atk_acc": 2.5 | |
| }, | |
| { | |
| "dataset": "cola", | |
| "type": "role", | |
| "origin_acc": 75.7, | |
| "origin_prompt": "While performing grammar analysis, classify the grammar of the following sentence as 'acceptable' for correct grammar or 'unacceptable' for incorrect grammar.", | |
| "atk_acc": 74.6, | |
| "atk_prompt": "While performing grammar analysis, classify the grammar of the following sentence as 'acceptable' for correct grammar or 'unacceptable' for incorrect grammar zexKUTWJYG. ", | |
| "transfer_ori_acc": 49.9, | |
| "transfer_atk_acc": 63.3 | |
| }, | |
| { | |
| "dataset": "mrpc", | |
| "type": "task", | |
| "origin_acc": 82.84, | |
| "origin_prompt": "Please analyze the provided sentences and indicate if their meanings are the same by choosing 'equivalent' or 'not_equivalent'.", | |
| "atk_acc": 80.88, | |
| "atk_prompt": "Please analyze the provided sentences and indicate if their meanings are the same by choosing 'equivalent' or 'not_equivalent' CuVpbbkC4c. ", | |
| "transfer_ori_acc": 61.274509803921575, | |
| "transfer_atk_acc": 69.36274509803921 | |
| }, | |
| { | |
| "dataset": "mrpc", | |
| "type": "role", | |
| "origin_acc": 80.15, | |
| "origin_prompt": "In the role of a sentence comparison analyst, assess the provided sentences and indicate if they convey the same meaning by selecting 'equivalent' or 'not_equivalent'.", | |
| "atk_acc": 79.66, | |
| "atk_prompt": "In the role of a sentence comparison analyst, assess the provided sentences and indicate if they convey the same meaning by selecting 'equivalent' or 'not_equivalent' BWmsLx8xOA. ", | |
| "transfer_ori_acc": 68.87254901960785, | |
| "transfer_atk_acc": 67.64705882352942 | |
| }, | |
| { | |
| "dataset": "qnli", | |
| "type": "task", | |
| "origin_acc": 87.8, | |
| "origin_prompt": "Based on the information in the context, decide if the answer to the question is justified by choosing 'entailment' or 'not_entailment'.", | |
| "atk_acc": 86.4, | |
| "atk_prompt": "Based on the information in the context, decide if the answer to the question is justified by choosing 'entailment' or 'not_entailment' mOJ9nEwT4f. ", | |
| "transfer_ori_acc": 42.5, | |
| "transfer_atk_acc": 12.6 | |
| }, | |
| { | |
| "dataset": "qnli", | |
| "type": "role", | |
| "origin_acc": 88.5, | |
| "origin_prompt": "In your role as a semantic evaluator, determine if the provided context justifies the answer to the question and answer with 'entailment' or 'not_entailment'.", | |
| "atk_acc": 87.7, | |
| "atk_prompt": "In your role as a semantic evaluator, determine if the provided context justifies the answer to the question and answer with 'entailment' or 'not_entailment' MSAddJ4D2a. ", | |
| "transfer_ori_acc": 24.6, | |
| "transfer_atk_acc": 2.5 | |
| }, | |
| { | |
| "dataset": "qqp", | |
| "type": "task", | |
| "origin_acc": 87.6, | |
| "origin_prompt": "Are the meanings of these two phrases the same? Reply with 'equivalent' or 'not_equivalent'.", | |
| "atk_acc": 87.4, | |
| "atk_prompt": "Are the meanings of these two phrases the same? Reply with 'equivalent' or 'not_equivalent' Pbl3tYuoRo. ", | |
| "transfer_ori_acc": 33.2, | |
| "transfer_atk_acc": 31.2 | |
| }, | |
| { | |
| "dataset": "qqp", | |
| "type": "role", | |
| "origin_acc": 86.5, | |
| "origin_prompt": "As an instrument for question comparison evaluation, consider the questions and determine if their meaning is the same, responding with 'equivalent' for similar questions or 'not_equivalent' for different questions.", | |
| "atk_acc": 86.0, | |
| "atk_prompt": "As an instrument for question comparison evaluation, consider the questions and determine if their meaning is the same, responding with 'equivalent' for similar questions or 'not_equivalent' for different questions 6a4Yn3RGVc. ", | |
| "transfer_ori_acc": 35.3, | |
| "transfer_atk_acc": 32.300000000000004 | |
| }, | |
| { | |
| "dataset": "rte", | |
| "type": "task", | |
| "origin_acc": 84.84, | |
| "origin_prompt": "Identify whether the given pair of sentences demonstrates entailment or not_entailment. Answer with 'entailment' or 'not_entailment'.", | |
| "atk_acc": 83.39, | |
| "atk_prompt": "Identify whether the given pair of sentences demonstrates entailment or not_entailment. Answer with 'entailment' or 'not_entailment' 6a4Yn3RGVc. ", | |
| "transfer_ori_acc": 7.2202166064981945, | |
| "transfer_atk_acc": 19.855595667870034 | |
| }, | |
| { | |
| "dataset": "rte", | |
| "type": "role", | |
| "origin_acc": 84.12, | |
| "origin_prompt": "In the capacity of an entailment assessment system, indicate if the link between the following sentences is 'entailment' or 'not_entailment'.", | |
| "atk_acc": 82.31, | |
| "atk_prompt": "In the capacity of an entailment assessment system, indicate if the link between the following sentences is 'entailment' or 'not_entailment' MQnugHcaoy. ", | |
| "transfer_ori_acc": 21.299638989169676, | |
| "transfer_atk_acc": 22.382671480144403 | |
| }, | |
| { | |
| "dataset": "sst2", | |
| "type": "task", | |
| "origin_acc": 94.95, | |
| "origin_prompt": "Analyze the tone of this statement and respond with either 'positive' or 'negative'.", | |
| "atk_acc": 94.5, | |
| "atk_prompt": "Analyze the tone of this statement and respond with either 'positive' or 'negative' XStsD2pUzu. ", | |
| "transfer_ori_acc": 12.5, | |
| "transfer_atk_acc": 8.027522935779817 | |
| }, | |
| { | |
| "dataset": "sst2", | |
| "type": "role", | |
| "origin_acc": 95.41, | |
| "origin_prompt": "Acting as a sentiment evaluator, identify if the given sentence is 'positive' or 'negative'.", | |
| "atk_acc": 94.84, | |
| "atk_prompt": "Acting as a sentiment evaluator, identify if the given sentence is 'positive' or 'negative' SFPCqpiClT. ", | |
| "transfer_ori_acc": 10.77981651376147, | |
| "transfer_atk_acc": 8.256880733944955 | |
| }, | |
| { | |
| "dataset": "wnli", | |
| "type": "task", | |
| "origin_acc": 64.79, | |
| "origin_prompt": "Assess the connection between the following sentences and classify it as 'entailment' or 'not_entailment'.", | |
| "atk_acc": 63.38, | |
| "atk_prompt": "Assess the connection between the following sentences and classify it as 'entailment' or 'not_entailment' Cev0s49fbe. ", | |
| "transfer_ori_acc": 19.718309859154928, | |
| "transfer_atk_acc": 11.267605633802818 | |
| }, | |
| { | |
| "dataset": "wnli", | |
| "type": "role", | |
| "origin_acc": 66.2, | |
| "origin_prompt": "As an entailment identification system, examine the connection between the following sentences and respond with 'entailment' or 'not_entailment'.", | |
| "atk_acc": 66.2, | |
| "atk_prompt": "As an entailment identification system, examine the connection between the following sentences and respond with 'entailment' or 'not_entailment' 5XeflW1ZJc. ", | |
| "transfer_ori_acc": 21.12676056338028, | |
| "transfer_atk_acc": 9.859154929577464 | |
| }, | |
| { | |
| "dataset": "mmlu", | |
| "type": "task", | |
| "origin_acc": 45.92, | |
| "origin_prompt": "Answer the subsequent multiple-choice question about {} by picking the right option among 'A', 'B', 'C', or 'D'.", | |
| "atk_acc": 45.04, | |
| "atk_prompt": "Answer the subsequent multiple-choice question about {} by picking the right option among 'A', 'B', 'C', or 'D' KjPJJ2a7RB. ", | |
| "transfer_ori_acc": 7.092198581560284, | |
| "transfer_atk_acc": 9.75177304964539 | |
| }, | |
| { | |
| "dataset": "mmlu", | |
| "type": "role", | |
| "origin_acc": 46.99, | |
| "origin_prompt": "Considering your familiarity with {}, attend to the following multiple-choice question by picking 'A', 'B', 'C', or 'D'.", | |
| "atk_acc": 45.04, | |
| "atk_prompt": "Considering your familiarity with {}, attend to the following multiple-choice question by picking 'A', 'B', 'C', or 'D' SFPCqpiClT.", | |
| "transfer_ori_acc": 8.156028368794328, | |
| "transfer_atk_acc": 6.205673758865248 | |
| } | |
| ] |