PrefRAG：偏好驱动的多源检索增强生成
PrefRAG: Preference-Driven Multi-Source Retrieval Augmented Generation
AI总结：
本文提出PrefRAG，一种偏好驱动的多源自适应检索增强生成系统，通过自适应检索、网络补充与答案质量反馈优化来源选择，性能显著超越Vanilla RAG和MS-ARAG。
摘要：
检索增强生成（RAG）已成为一种可靠的外部知识增强技术，用于缓解大语言模型（LLMs）中的幻觉问题和参数化知识局限。现有的自适应RAG（ARAG）系统擅长在单一来源内进行深入探索，但难以有效且可控地探索不同的检索来源，因为它们无法预见其内部知识特征。我们开发了一种新颖的多源ARAG系统PrefRAG，该系统通过偏好驱动的自适应检索和自我反思，实现对多样化检索来源的深入且可控探索，从而增强RAG。PrefRAG首先在自适应检索中充分探索可控的本地来源，并在适当时用网络进行补充，最终选择最优来源进行知识观察。随后，PrefRAG将答案质量反馈输入检索过程，从生成角度对其进行优化，以产生更高质量的回答。大量实验证实了其优越性、高检索效率和知识可控性。PrefRAG分别比Vanilla RAG和领先的MS-ARAG性能提升高达25.6%和13.9%。此外，使用DPO训练的PrefRAG取得了更高的性能。代码和数据可在https://github.com/QingFei1/PrefRAG.git获取。
英文摘要：
Retrieval-Augmented Generation (RAG) has emerged as a reliable external knowledge augmentation technique to mitigate hallucination issues and parameterized knowledge limitations in Large Language Models (LLMs). Existing adaptive RAG (ARAG) systems excel at in-depth exploration within a single source but struggle to effectively and controllably explore different retrieval sources, as they fail to foresee their internal knowledge features. We develop a novel multi-source ARAG system, PrefRAG, which enhances RAG by enabling in-depth and controllable exploration of diverse retrieval sources through preference-driven adaptive retrieval and self-reflection. PrefRAG first fully explores controllable local sources in adaptive retrieval and supplements with the web when appropriate, ultimately selecting the optimal source for knowledge observation. Subsequently, PrefRAG feeds answer quality feedback into the retrieval process, optimizing it from the generation perspective to produce higher-quality responses. Extensive experiments confirm its superiority, high retrieval efficiency, and knowledge controllability. PrefRAG outperforms Vanilla RAG and the leading MS-ARAG by up to 25.6% and 13.9% respectively. Additionally, PrefRAG trained with DPO achieves higher performance. The code and data are available at https://github.com/QingFei1/PrefRAG.git.
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。
