发表机构
ETH Zürich; University of Twente（苏黎世联邦理工学院; 特温特大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本研究提出新型RAG扩展GuidedRAG，通过检索前语义约束缩小搜索空间，大幅提升检索相关性、精度、效率及用户意图对齐度，且泛化至15种RAG变体，为改进RAG提供了强大范式。
AI 中文摘要
本研究提出GuidedRAG，这是传统检索增强生成（Retrieval-Augmented Generation，RAG）的新型扩展，在检索过程中引入了专用选择阶段与语义引导。与当前最先进的RAG方法依赖日益复杂的检索和知识结构不同，GuidedRAG在检索前通过语义约束知识库，使检索空间与用户意图对齐，同时大幅缩小搜索空间。我们的评估显示，GuidedRAG将检索相关性提升14.0%-15.8%，缓解19.7%-27.4%的检索精度损失，将检索开销降低数个数量级；此外，相关片段在排序过程中被更早检索到，与用户意图的对齐度提升31.8%-36.8%。我们进一步验证，GuidedRAG在15种不同的RAG变体中实现了全覆盖，展现出跨文献的泛化能力。这些发现共同确立了语义引导与选择作为强大且可泛化的范式，用于改进当前最先进的RAG技术。
英文摘要
In this work, we propose GuidedRAG, a novel extension to traditional Retrieval-Augmented Generation (RAG) that introduces a dedicated selection stage and semantic steering during retrieval. In contrast to current state-of-the-art RAG approaches, which depend on increasingly complex retrieval and knowledge structures, GuidedRAG constrains the knowledge base using semantics before retrieval, aligning the retrieval space with user intent while substantially reducing the search space. Our evaluation shows that GuidedRAG improves retrieval relevance by 14.0-15.8%, mitigates a 19.7-27.4% loss in retrieval precision, and reduces retrieval overhead by orders of magnitude. Moreover, relevant chunks are consistently retrieved earlier in the ranking process, while alignment with user intent improves by 31.8-36.8%. We further show that GuidedRAG achieves full coverage across 15 diverse RAG variants, demonstrating generalizability across the literature. Together, these findings establish semantic steering and selections as a powerful and generalizable paradigm for improving the current state-of-the-art in RAG.
Comments8 pages + 5 pages of references and appendix. 8 figures and 6 tables
