arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2411.14572cs.LGcs.CL

面向检索增强生成中的知识检查:一种表示视角

Towards Knowledge Checking in Retrieval-augmented Generation: A Representation Perspective

Michigan State University(密歇根州立大学)

Shenglai Zeng, Jiankun Zhang, Bingheng Li, Yuping Lin, Tianqi Zheng, Dante Everaert, Hanqing Lu, Hui Liu, Hui Liu, Yue Xing, Monica Xiao Cheng, Jiliang Tang

AI总结:

本文从表示视角系统研究RAG系统中的知识检查问题,通过分析LLM表示行为并构建基于表示的分类器进行知识过滤,在含噪知识库条件下显著提升了RAG性能。

摘要:

检索增强生成(RAG)系统已在提升大语言模型(LLMs)性能方面展现出潜力。然而,这些系统在有效整合外部知识与大语言模型内部知识方面面临挑战,常常导致误导性或无用信息的产生。本工作旨在对RAG系统中的知识检查进行系统性研究。我们对大语言模型的表示行为进行了全面分析,并证明了利用表示进行知识检查的重要性。受这些发现的启发,我们进一步开发了基于表示的分类器用于知识过滤。我们展示了即使在面对含噪知识数据库时,RAG性能也能得到显著提升。本研究为利用大语言模型表示来增强RAG系统的可靠性和有效性提供了新的见解。

英文摘要:

Retrieval-Augmented Generation (RAG) systems have shown promise in enhancing the performance of Large Language Models (LLMs). However, these systems face challenges in effectively integrating external knowledge with the LLM's internal knowledge, often leading to issues with misleading or unhelpful information. This work aims to provide a systematic study on knowledge checking in RAG systems. We conduct a comprehensive analysis of LLM representation behaviors and demonstrate the significance of using representations in knowledge checking. Motivated by the findings, we further develop representation-based classifiers for knowledge filtering. We show substantial improvements in RAG performance, even when dealing with noisy knowledge databases. Our study provides new insights into leveraging LLM representations for enhancing the reliability and effectiveness of RAG systems.

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。

↑