Graph-Guided Concept Selection for Efficient Retrieval-Augmented Generation
This addresses efficiency issues in RAG for domains like biomedicine and law, offering a cost-effective solution with incremental improvements over existing methods.
The paper tackles the high computational cost of graph-based retrieval-augmented generation (RAG) by proposing Graph-Guided Concept Selection (G2ConS), which reduces LLM calls for knowledge graph construction and improves retrieval and answering quality across multiple real-world datasets.
Graph-based RAG constructs a knowledge graph (KG) from text chunks to enhance retrieval in Large Language Model (LLM)-based question answering. It is especially beneficial in domains such as biomedicine, law, and political science, where effective retrieval often involves multi-hop reasoning over proprietary documents. However, these methods demand numerous LLM calls to extract entities and relations from text chunks, incurring prohibitive costs at scale. Through a carefully designed ablation study, we observe that certain words (termed concepts) and their associated documents are more important. Based on this insight, we propose Graph-Guided Concept Selection (G2ConS). Its core comprises a chunk selection method and an LLM-independent concept graph. The former selects salient document chunks to reduce KG construction costs; the latter closes knowledge gaps introduced by chunk selection at zero cost. Evaluations on multiple real-world datasets show that G2ConS outperforms all baselines in construction cost, retrieval effectiveness, and answering quality.