Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2510.24120 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866914117920489472 |
|---|---|
| author | Liu, Ziyu Liu, Yijing Yuan, Jianfei Yan, Minzhi Yue, Le Xiong, Honghui Yang, Yi |
| author_facet | Liu, Ziyu Liu, Yijing Yuan, Jianfei Yan, Minzhi Yue, Le Xiong, Honghui Yang, Yi |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2510_24120 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Graph-Guided Concept Selection for Efficient Retrieval-Augmented Generation Liu, Ziyu Liu, Yijing Yuan, Jianfei Yan, Minzhi Yue, Le Xiong, Honghui Yang, Yi Machine Learning 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. |
| title | Graph-Guided Concept Selection for Efficient Retrieval-Augmented Generation |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2510.24120 |