Year: 2026
Type: conference-paper
Abstract: Retrieval-Augmented Generation enhances language models by retrieving external knowledge to support informed and grounded responses.However, traditional RAG methods rely on fragment-level retrieval, limiting their ability to address query-focused summarization queries.GraphRAG introduces a graphbased paradigm for global knowledge reasoning, yet suffers from inefficiencies in information extraction, costly resource consumption, and poor adaptability to incremental updates.To overcome these limitations, we propose TagRAG, a tag-guided hierarchical knowledge graph RAG framework designed for efficient global reasoning and scalable graph maintenance.TagRAG introduces two key components: (1) Tag Knowledge Graph Construction, which extracts object tags and their relationships from documents and organizes them into hierarchical domain tag chains for structured knowledge representation, and (2) Tag-Guided Retrieval-Augmented Generation, which retrieves domain-centric tag chains to localize and synthesize relevant knowledge during inference.This design significantly adapts to smaller language models, improves retrieval granularity, and supports efficient knowledge increment.Extensive experiments on Ultra-Domain datasets spanning Agriculture, Computer Science, Law, and cross-domain settings demonstrate that TagRAG achieves an average winning rate of 78.36% against baselines while maintaining about 14.6x construction and 1.9x retrieval efficiency compared with GraphRAG.... ...
Authors: Wenbiao Tao, Xinyuan Li, Yunshi Lan, Weining Qian
Institution: East China Normal University
Language: English
Topic: Topic Modeling
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: hybrid
Award: G4092946432
OpenAlex ID: W7166847319