Spaces:
Runtime error
Runtime error
File size: 7,660 Bytes
683d0f6 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 |
[
{
"dataset": "cola",
"type": "task",
"origin_acc": 69.0,
"origin_prompt": "Assess the following sentence and determine if it is grammatically correct. Respond with 'Acceptable' or 'Unacceptable':",
"atk_acc": 1.7,
"atk_prompt": "check the below verb and consider if it is grammatically complete. act with 'Acceptable' or 'Unacceptable':",
"transfer_ori_acc": 76.5,
"transfer_atk_acc": 74.0
},
{
"dataset": "cola",
"type": "role",
"origin_acc": 57.1,
"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": 0.6,
"atk_prompt": "as as a grammar evaluation resource, analyze the next phrase and decide if it is grammatical+ correct, respond with 'acceptable' or 'unacceptable':",
"transfer_ori_acc": 79.5,
"transfer_atk_acc": 75.5
},
{
"dataset": "mrpc",
"type": "task",
"origin_acc": 67.16,
"origin_prompt": "Are the meanings of the following pair of sentences the same? Answer with 'equivalent' or 'not_equivalent'.",
"atk_acc": 0.0,
"atk_prompt": "Are the meanings of the next in of sentences the same? q with 'equivalent' or 'not_equivalent'. ",
"transfer_ori_acc": 72.5,
"transfer_atk_acc": 68.5
},
{
"dataset": "mrpc",
"type": "role",
"origin_acc": 52.21,
"origin_prompt": "In your capacity as a semantic comparison tool, examine the given sentences and decide if their meanings are identical, responding with 'equivalent' or 'not_equivalent'.",
"atk_acc": 0.0,
"atk_prompt": "[UNK] your capacity as a semantic comparison tool, examine the given sentences and decide if their meanings are different, responding with 'equivalent' or 'not_equivalent'. ",
"transfer_ori_acc": 75.0,
"transfer_atk_acc": 62.5
},
{
"dataset": "qnli",
"type": "task",
"origin_acc": 30.5,
"origin_prompt": "Review the given context and question, and decide if the context contains enough information to support the answer by selecting 'entailment' or 'not_entailment'.",
"atk_acc": 0.0,
"atk_prompt": "Review the given context and question, and decide if the context requires enough information to let the answer by choices 'entailment' or 'not_entailment'. ",
"transfer_ori_acc": 64.5,
"transfer_atk_acc": 63.5
},
{
"dataset": "qnli",
"type": "role",
"origin_acc": 38.4,
"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": 0.4,
"atk_prompt": "example a textual in expert, analyzing if the answer to the question can be deduced from the language context and think 'entailment' or 'not_entailment'. ",
"transfer_ori_acc": 80.0,
"transfer_atk_acc": 63.0
},
{
"dataset": "qqp",
"type": "task",
"origin_acc": 23.9,
"origin_prompt": "Can these two statements be considered equal in meaning? Answer with 'equivalent' or 'not_equivalent'.",
"atk_acc": 0.8,
"atk_prompt": "can these two symbols be considered equal in meaning? object with 'equivalent' or 'not_equivalent'. ",
"transfer_ori_acc": 81.0,
"transfer_atk_acc": 12.0
},
{
"dataset": "qqp",
"type": "role",
"origin_acc": 0,
"origin_prompt": "",
"atk_acc": 100,
"atk_prompt": "",
"transfer_ori_acc": 0.0,
"transfer_atk_acc": 0.0
},
{
"dataset": "rte",
"type": "task",
"origin_acc": 47.65,
"origin_prompt": "Please classify the relationship between the provided sentences as 'entailment' or 'not_entailment'.",
"atk_acc": 0.0,
"atk_prompt": "Please approach the relationship between the included sentences as 'entailment' or 'not_entailment'.",
"transfer_ori_acc": 79.5,
"transfer_atk_acc": 81.5
},
{
"dataset": "rte",
"type": "role",
"origin_acc": 48.01,
"origin_prompt": "As an entailment identification system, examine the connection between the following sentences and respond with 'entailment' or 'not_entailment':",
"atk_acc": 1.44,
"atk_prompt": "she an entailment identification system, presented the connection between the following sentences and answered with 'entailment' or 'not_entailment':",
"transfer_ori_acc": 76.0,
"transfer_atk_acc": 75.5
},
{
"dataset": "sst2",
"type": "task",
"origin_acc": 48.17,
"origin_prompt": "After examining the following expression, label its emotion as either 'positive' or 'negative':",
"atk_acc": 0.57,
"atk_prompt": "After examination the given expression, type its emotion as of 'positive' or 'negative': ",
"transfer_ori_acc": 90.0,
"transfer_atk_acc": 92.0
},
{
"dataset": "sst2",
"type": "role",
"origin_acc": 37.27,
"origin_prompt": "As an emotion detector, determine if the provided passage conveys a 'positive' or 'negative' sentiment. Classify:",
"atk_acc": 0.46,
"atk_prompt": "As an emotion indicating, score if the provided reply conveys a 'positive' or 'negative' sentiment. classify: ",
"transfer_ori_acc": 88.5,
"transfer_atk_acc": 91.0
},
{
"dataset": "wnli",
"type": "task",
"origin_acc": 43.66,
"origin_prompt": "Determine if the given pair of sentences displays entailment or not_entailment. Respond with 'entailment' or 'not_entailment'.",
"atk_acc": 0.0,
"atk_prompt": "Determine if the first pair of sentences demonstrate entailment or not_entailment. replied with 'entailment' or 'not_entailment'.",
"transfer_ori_acc": 63.38028169014085,
"transfer_atk_acc": 60.56338028169014
},
{
"dataset": "wnli",
"type": "role",
"origin_acc": 43.66,
"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": 0.0,
"atk_prompt": "In your role as an entailment analysis tool, assessing the relationship between the formed sentences and classify it as 'entailment' or 'not_entailment':",
"transfer_ori_acc": 52.112676056338024,
"transfer_atk_acc": 52.112676056338024
},
{
"dataset": "mmlu",
"type": "task",
"origin_acc": 25.09,
"origin_prompt": "Answer the subsequent multiple-choice question about {} by picking the right option among 'A', 'B', 'C', or 'D'.",
"atk_acc": 5.02,
"atk_prompt": "Answer the next multiple-s question about {} by picking the incorrect button or 'A', 'B', 'C', or 'D'. ",
"transfer_ori_acc": 62.0,
"transfer_atk_acc": 26.0
},
{
"dataset": "mmlu",
"type": "role",
"origin_acc": 24.85,
"origin_prompt": "As an expert in {}, respond to the following multiple-choice question by selecting 'A', 'B', 'C', or 'D'.",
"atk_acc": 6.88,
"atk_prompt": "As an expert in {}, answer to the following multiple-guessing contestant by guessing 'A', 'B', 'C', or 'D'.",
"transfer_ori_acc": 61.5,
"transfer_atk_acc": 60.0
}
] |