mlsanityData to 14 Oct 2026

Graph-Guided Concept Selection for Efficient Retrieval-Augmented Generation

arXiv 2510.24120 ↗First posted 28 Oct 2025cs.LGcited by 0

On the map: Retrieval-augmented generation → Knowledge-graph and structured-knowledge RAG

Abstract (arXiv)

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.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Knowledge-graph and structured-knowledge RAG, one of 15 directions in Retrieval-augmented generation. Builds on 24 of its 33 references that are in the map. First posted on arXiv 28 Oct 2025.

Builds on

24 of 33 references.

Closest ancestors · 9

Same direction, newest first

  1. 2025Retrieval-Augmented Generation with Hierarchical Knowledge13 Mar
  2. 2025PathRAG: Pruning Graph-based Retrieval Augmented Generation with Relational Paths18 Feb
  3. 2025ArchRAG: Attributed Community-based Hierarchical Retrieval-Augmented Generation14 Feb
  4. 2025KET-RAG: A Cost-Efficient Multi-Granular Indexing Framework for Graph-RAG13 Feb
  5. 2024FastRAG: Retrieval Augmented Generation for Semi-structured Data21 Nov
  6. 2024LightRAG: Simple and Fast Retrieval-Augmented Generation8 Oct
  7. 2024Graph Retrieval-Augmented Generation: A Survey15 Aug
  8. 2024From Local to Global: A Graph RAG Approach to Query-Focused Summarization24 Apr
  9. 2024RAPTOR: Recursive Abstractive Processing for Tree-Organized Retrieval31 Jan

Other references · 15

  1. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,297
  2. 2018HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answeringcited by 3,754
  3. 2023Retrieval-Augmented Generation for Large Language Models: A Surveycited by 2,212
  4. 2021MuSiQue: Multihop Questions via Single-hop Question Compositioncited by 916
  5. 2022Precise Zero-Shot Dense Retrieval without Relevance Labelscited by 517
  6. 2024A Survey on RAG Meeting LLMs: Towards Retrieval-Augmented Large Language Modelscited by 452
  7. 2019Dice Loss for Data-imbalanced NLP Taskscited by 182
  8. 2023Knowledge Graph Prompting for Multi-Document Question Answeringcited by 152
  9. 2023Walking Down the Memory Maze: Beyond Context Limit through Interactive Readingcited by 133
  10. 2024HybridRAG: Integrating Knowledge Graphs and Vector Retrieval Augmented Generation for Efficient Information Extractioncited by 93
  11. 2019Knowledge Guided Text Retrieval and Reading for Open Domain Question Answeringcited by 59
  12. 2024DALK: Dynamic Co-Augmentation of LLMs and KG to answer Alzheimer's Disease Questions with Scientific Literaturecited by 50
3 more
  1. 2024GraphReader: Building Graph-based Agent to Enhance Long-Context Abilities of Large Language Modelscited by 43
  2. 2024Graph-Based Retriever Captures the Long Tail of Biomedical Knowledgecited by 20
  3. 2023AutoKG: Efficient Automated Knowledge Graph Generation for Language Modelscited by 17

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025Clue-RAG: Towards Accurate and Cost-Efficient Graph-based RAG via Multi-Partite Graph and Query-Driven Iterative Retrieval
  2. 2026Efficient Retrieval-Augmented Generation via Token Co-occurrence Graphs
  3. 2024Think-on-Graph 2.0: Deep and Faithful Large Language Model Reasoning with Knowledge-guided Retrieval Augmented Generation
  4. 2025Beyond Static Retrieval: Opportunities and Pitfalls of Iterative Retrieval in GraphRAG
  5. 2025Query-Centric Graph Retrieval Augmented Generation
  6. 2024SimGRAG: Leveraging Similar Subgraphs for Knowledge Graphs Driven Retrieval-Augmented Generation
  7. 2024Simple Is Effective: The Roles of Graphs and Large Language Models in Knowledge-Graph-Based Retrieval-Augmented Generation
  8. 2025Graph-based Approaches and Functionalities in Retrieval-Augmented Generation: A Comprehensive Survey