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": 69.0, | |
| "transfer_atk_acc": 44.1 | |
| }, | |
| { | |
| "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": 32.35294117647059, | |
| "transfer_atk_acc": 39.950980392156865 | |
| }, | |
| { | |
| "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": 26.5, | |
| "transfer_atk_acc": 17.9 | |
| }, | |
| { | |
| "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": 23.9, | |
| "transfer_atk_acc": 2.3 | |
| }, | |
| { | |
| "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": 27.075812274368232, | |
| "transfer_atk_acc": 16.60649819494585 | |
| }, | |
| { | |
| "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": 32.798165137614674, | |
| "transfer_atk_acc": 49.19724770642202 | |
| }, | |
| { | |
| "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": 25.352112676056336, | |
| "transfer_atk_acc": 14.084507042253522 | |
| }, | |
| { | |
| "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": 22.69503546099291, | |
| "transfer_atk_acc": 28.368794326241137 | |
| } | |
| ] |