NCSOFT/offsetbias
收藏数据集卡片:OffsetBias
数据集描述
数据集概述
OffsetBias 是一个成对偏好数据集,旨在减少评估模型(专门用于评估的语言模型)中固有的常见偏差。该数据集包含8,504个样本,用于训练评估(或奖励)模型。
数据集结构
数据实例
json { "instruction": "Rewrite the following sentence, paying attention to spelling and grammar. Distance learning is harder then in-person classes", "output_1": "Distance learning is harder than in-person classes.", "output_2": "The original sentence is grammatically correct and the punctuation is also appropriate. However, if you wish to slightly rephrase it for clarity or emphasis, one possibility is:
"Studying online can be more challenging than in traditional classroom settings."
This slight tweak emphasizes the comparison between "studying online" and "studying... in traditional classroom settings."", "label": 1 }
数据字段
instruction: 字符串,响应需要回答的指令output_1: 字符串,第一个候选响应output_2: 字符串,第二个候选响应label: 整数,1或2,表示更好的响应编号
数据集构建
指令来自包括Alpaca、Ultrachat、Evol-Instruct和Flan在内的源数据集。输出使用GPT-3.5、GPT-4和Claude-3-Opus模型生成。
数据使用注意事项
该数据集旨在作为现有评估模型中常见偏差的反例集合。因此,单独使用此数据集进行训练不适合训练评估模型,因为它会引入另一种偏差。最好将其用作可以补充其他通用评估数据集的附加数据集。
引用
bibtex @misc{park2024offsetbias, title={OffsetBias: Leveraging Debiased Data for Tuning Evaluators}, author={Junsoo Park and Seungyeon Jwa and Meiying Ren and Daeyoung Kim and Sanghyuk Choi}, year={2024}, eprint={2407.06551}, archivePrefix={arXiv}, primaryClass={cs.CL} }




