arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2408.10573cs.CLcs.AI
收藏

将人置于大语言模型的视角:通过问题重写器生成更好的答案

Putting People in LLMs' Shoes: Generating Better Answers via Question Rewriter

Osaka University(大阪大学)

Junhao Chen, Bowen Wang, Zhouqiang Jiang, Yuta Nakashima

AI总结:

提出问题重写器,通过单轮实例级提示优化增强人类问题对黑盒LLMs的可理解性,利用直接偏好优化训练,无需人工标注,在多个黑盒LLMs和LFQA数据集上提升答案质量。

摘要:

大语言模型(LLMs)已展现出显著的能力,特别是在问答(QA)领域。然而,它们在问答中的有效性常常受到用户问题模糊性的削弱。为解决这一问题,我们引入了单轮实例级提示优化,称为问题重写器。通过增强人类问题对黑盒LLMs的可理解性,我们的问题重写器提高了生成答案的质量。该重写器基于自动评估生成答案的标准所收集的反馈,使用直接偏好优化进行优化;因此,其训练不需要昂贵的人工标注。在多个黑盒LLMs和长形式问答(LFQA)数据集上的实验证明了我们方法的有效性。本文为训练问题重写器提供了一个实用框架,并为未来在LFQA任务中探索提示优化树立了先例。代码可在https://github.com/3244we/Question-Rewriter获取。

英文摘要:

Large Language Models (LLMs) have demonstrated significant capabilities, particularly in the domain of question answering (QA). However, their effectiveness in QA is often undermined by the vagueness of user questions. To address this issue, we introduce single-round instance-level prompt optimization, referred to as question rewriter. By enhancing the intelligibility of human questions for black-box LLMs, our question rewriter improves the quality of generated answers. The rewriter is optimized using direct preference optimization based on feedback collected from automatic criteria for evaluating generated answers; therefore, its training does not require costly human annotations. The experiments across multiple black-box LLMs and long-form question answering (LFQA) datasets demonstrate the efficacy of our method. This paper provides a practical framework for training question rewriters and sets a precedent for future explorations in prompt optimization within LFQA tasks. Code is available at https://github.com/3244we/Question-Rewriter.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑