{"ID":2848947,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2510.24120","arxiv_id":"2510.24120","title":"Graph-Guided Concept Selection for Efficient Retrieval-Augmented Generation","abstract":"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.","short_abstract":"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....","url_abs":"https://arxiv.org/abs/2510.24120","url_pdf":"https://arxiv.org/pdf/2510.24120v1","authors":"[\"Ziyu Liu\",\"Yijing Liu\",\"Jianfei Yuan\",\"Minzhi Yan\",\"Le Yue\",\"Honghui Xiong\",\"Yi Yang\"]","published":"2025-10-28T06:47:30Z","proceeding":"cs.LG","tasks":"[\"cs.LG\"]","methods":"[\"RAG\",\"Large Language Model\",\"Language Model\"]","has_code":false}