analiza aiqbench
GuidedRAG introduces semantic steering as a dedicated pre-retrieval stage, effectively narrowing the search space for Retrieval-Augmented Generation systems without relying on increasingly complex knowledge structures. This approach significantly boosts retrieval relevance and user intent alignment while drastically cutting computational overhead compared to current state-of-the-art methods. The technique demonstrates broad generalizability across 15 diverse RAG variants, marking a step toward more efficient and precise AI information access.
GuidedRAG: Semantic Steering of Retrieval-Augmented Generation
arXiv:2607.26071v1 Announce Type: cross Abstract: 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.
Abstract: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.
8 pages + 5 pages of references and appendix. 8 figures and 6 tables
Information Retrieval (cs.IR); Artificial Intelligence (cs.AI)
arXiv:2607.26071 [cs.IR]
(or arXiv:2607.26071v1 [cs.IR] for this version)
https://doi.org/10.48550/arXiv.2607.26071 Focus to learn more arXiv-issued DOI via DataCite
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Text integral sub licența deschisă a publicației · 255 cuvinte
Subiecte conexe
SEEK: Steering LLM Reasoning for RAG via Internal Reasoning Sketches
arXiv · 8 iun. 2026
EventOD: Event-Aware OD Flow Generation via LLM-Guided Semantic Modulation
arXiv · 28 iul. 2026
TriShieldRAG: A Three-Ring Defense-in-Depth Framework Against Knowledge Corruption in Retrieval-Augmented Generation
arXiv · 28 iul. 2026
Automating coherent long-form video generation
Google Research · 24 sept. 2026