通过偏好驱动实现多源检索的可控高效生成，显著提升大模型回答质量。
PrefRAG: Preference-Driven Multi-Source Retrieval Augmented Generation
- 基于偏好学习动态选择最优检索源，实现多源可控探索。
- 相比基线模型，答案准确率最高提升25.6%，检索效率更高。
- 适合需要精准知识控制与高质量生成的应用场景。
检索增强生成（RAG）已成为缓解大语言模型幻觉和参数化知识局限性的可靠外部知识增强技术。现有自适应RAG（ARAG）系统在单一来源内能深入探索，但难以有效且可控地跨源检索，因无法预判各源内部知识特征。本文提出新型多源ARAG系统PrefRAG，通过偏好驱动的自适应检索与自我反思机制，实现对多样化检索源的深度与可控探索。PrefRAG首先在可控本地源中自适应检索，必要时补充网络数据，最终选出最优知识源进行观察；随后将生成质量反馈回传至检索过程，从生成视角优化检索，生成更高质量结果。大量实验验证其优越性：相比基础RAG和领先多源ARAG，性能分别提升最高达25.6%和13.9%。使用DPO训练的PrefRAG表现更优。代码与数据已开源于https://github.com/QingFei1/PrefRAG.git。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。