Dynamic Graph Navigation via Triplet Chains for Structure-Aware Retrieval-Augmented Generation
Year: 2026
Type: conference-paper
Abstract: Retrieval-Augmented Generation (RAG) was proposed to address the hallucination question of large language models (LLMs).However, the traditional RAG framework has certain limitations: for simple questions, the search results often introduce a large amount of irrelevant information; while for complex questions, the lengthy reference knowledge provided by the retrieval lacks structural information.Therefore, we proposed a structureaware RAG, which achieves noise removal in retrieval through multi-chain graph navigation reasoning(Trig-Nav).This method constructs question triple reasoning chains and reference knowledge graphs with text attributes, allowing the system to retrieve three types of knowledge along different paths based on the requirements of LLM.It provides LLM with multi-angle and structured information input and significantly reduces noise.We conducted a comprehensive evaluation of Trig-Nav, comparing it with baseline methods across multiple datasets.Compared to traditional RAG, there is an average improvement of 6% in effectiveness.The results showed that Trig-Nav significantly enhances the model's performance, validating the effectiveness of this approach.
Authors: Feng Zhao, Yufei Wu, Xianggan Liu, Ruilin Zhao
Institution: Huazhong University of Science and Technology
Language: English
Topic: Topic Modeling
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: hybrid
Award: G4884346807
OpenAlex ID: W7166804131