TagRAG: Tag-guided Hierarchical Knowledge Graph Retrieval-Augmented Generation

TL;DR

TagRAG introduces a hierarchical, tag-guided knowledge graph retrieval framework that enhances efficiency and scalability for knowledge reasoning in language models, especially for query-focused tasks.

Contribution

It proposes a novel tag-guided hierarchical knowledge graph construction and retrieval method that improves efficiency, adaptability, and reasoning capabilities over existing graph-based RAG approaches.

Findings

Achieves 78.36% average winning rate against baselines.

Provides 14.6x faster graph construction and 1.9x faster retrieval.

Demonstrates effectiveness across diverse UltraDomain datasets.

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 graph-based 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 UltraDomain 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.