mlsanityData to 14 Oct 2026

Can Knowledge-Graph-based Retrieval Augmented Generation Really Retrieve What You Need?

arXiv 2510.16582 ↗First posted 18 Oct 2025cs.AIcited by 8

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

Abstract (arXiv)

Retrieval-Augmented Generation (RAG) based on knowledge graphs (KGs) enhances large language models (LLMs) by providing structured and interpretable external knowledge. However, existing KG-based RAG methods struggle to retrieve accurate and diverse information from text-rich KGs for complex real-world queries. Process Reward Models (PRMs) offer a way to align the retrieval process of KG-based RAG with query-specific knowledge requirements, but they heavily rely on process-level supervision signals that are expensive and hard to obtain on KGs. To address this challenge, we propose GraphFlow, a framework that efficiently retrieves accurate and diverse knowledge required for real-world queries from text-rich KGs. GraphFlow employs a transition-based flow matching objective to jointly optimize a retrieval policy and a flow estimator. The flow estimator factorizes the reward of the retrieval outcome into the intermediate retrieval states. Such reward factorization guides the retrieval policy to retrieve candidates from KGs in proportion to their reward. This allows GraphFlow to explore high-quality regions of KGs that yield diverse and relevant results. We evaluate GraphFlow on the STaRK benchmark, which includes real-world queries from multiple domains over text-rich KGs. GraphFlow outperforms strong KG-RAG baselines, including GPT-4o, by 10% on average in hit rate and recall. It also shows strong generalization to unseen KGs, demonstrating its effectiveness and robustness.

Key facts. Cited by 8 papers in the map (data through 14 Oct 2026). Placed in Knowledge-graph and structured-knowledge RAG, one of 15 directions in Retrieval-augmented generation. Builds on 77 of its 91 references that are in the map. First posted on arXiv 18 Oct 2025.

Builds on

77 of 91 references.

Closest ancestors · 11

Same direction, newest first

  1. 2025Weak-to-Strong GraphRAG: Aligning Weak Retrievers with Large Language Models for Graph-based Retrieval Augmented Generation26 Jun
  2. 2025HopRAG: Multi-Hop Reasoning for Logic-Aware Retrieval-Augmented Generation18 Feb
  3. 2025RAG vs. GraphRAG: A Systematic Evaluation and Key Insights17 Feb
  4. 2025GFM-RAG: Graph Foundation Model for Retrieval Augmented Generation3 Feb
  5. 2024Retrieval-Augmented Generation with Graphs (GraphRAG)31 Dec
  6. 2024KG-Retriever: Efficient Knowledge Indexing for Retrieval-Augmented Large Language Models7 Dec
  7. 2024Advanced RAG Models with Graph Structures: Optimizing Complex Knowledge Reasoning and Text Generation6 Nov
  8. 2024Think-on-Graph 2.0: Deep and Faithful Large Language Model Reasoning with Knowledge-guided Retrieval Augmented Generation15 Jul
  9. 2024GNN-RAG: Graph Neural Retrieval for Large Language Model Reasoning30 May
  10. 2024From Local to Global: A Graph RAG Approach to Query-Focused Summarization24 Apr
  11. 2024G-Retriever: Retrieval-Augmented Generation for Textual Graph Understanding and Question Answering12 Feb

Other references · 66

  1. 2022Training language models to follow instructions with human feedbackcited by 15,971
  2. 2024The Llama 3 Herd of Modelscited by 14,715
  3. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,361
  4. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,297
  5. 2019Sentence-BERT: Sentence Embeddings using Siamese BERT-Networkscited by 9,170
  6. 2020Dense Passage Retrieval for Open-Domain Question Answeringcited by 3,824
  7. 2023Let's Verify Step by Stepcited by 3,789
  8. 2023Tree of Thoughts: Deliberate Problem Solving with Large Language Modelscited by 3,211
  9. 2020Open Graph Benchmark: Datasets for Machine Learning on Graphscited by 2,163
  10. 2023A Survey on Hallucination in Large Language Models: Principles, Taxonomy, Challenges, and Open Questionscited by 1,601
  11. 2025Search-R1: Training LLMs to Reason and Leverage Search Engines with Reinforcement Learningcited by 1,444
  12. 2022Scaling Laws for Reward Model Overoptimizationcited by 1,095
38 more
  1. 2024SimPO: Simple Preference Optimization with a Reference-Free Rewardcited by 963
  2. 2023Improving and generalizing flow-based generative models with minibatch optimal transportcited by 879
  3. 2023Siren's Song in the AI Ocean: A Survey on Hallucination in Large Language Modelscited by 698
  4. 2023Unifying Large Language Models and Knowledge Graphs: A Roadmapcited by 668
  5. 2025Process Reinforcement through Implicit Rewardscited by 504
  6. 2024RewardBench: Evaluating Reward Models for Language Modelingcited by 499
  7. 2018Behavioral Cloning from Observationcited by 492
  8. 2018Scalable agent alignment via reward modeling: a research directioncited by 447
  9. 2025Search-o1: Agentic Search-Enhanced Large Reasoning Modelscited by 433
  10. 2025The Lessons of Developing Process Reward Models in Mathematical Reasoningcited by 415
  11. 2021QA-GNN: Reasoning with Language Models and Knowledge Graphs for Question Answeringcited by 388
  12. 2023Reasoning on Graphs: Faithful and Interpretable Large Language Model Reasoningcited by 328
  13. 2021GFlowNet Foundationscited by 290
  14. 2023Challenges and Applications of Large Language Modelscited by 254
  15. 2022Trajectory balance: Improved credit assignment in GFlowNetscited by 251
  16. 2022Bayesian Structure Learning with Generative Flow Networkscited by 153
  17. 2022Learning Causally Invariant Representations for Out-of-Distribution Generalization on Graphscited by 144
  18. 2025VisualPRM: An Effective Process Reward Model for Multimodal Reasoningcited by 139
  19. 2022Learning GFlowNets from partial episodes for improved convergence and stabilitycited by 132
  20. 2020Graph Information Bottleneck for Subgraph Recognitioncited by 119
  21. 2022Generative Flow Networks for Discrete Probabilistic Modelingcited by 114
  22. 2024Rule Based Rewards for Language Model Safetycited by 108
  23. 2023Amortizing intractable inference in large language modelscited by 97
  24. 2025Process Reward Models for LLM Agents: Practical Framework and Directionscited by 85
  25. 2023Towards Understanding and Improving GFlowNet Trainingcited by 75
  26. 2024Amortizing intractable inference in diffusion models for vision, language, and controlcited by 72
  27. 2024MOOSE-Chem: Large Language Models for Rediscovering Unseen Chemistry Scientific Hypothesescited by 72
  28. 2024KG-RAG: Bridging the Gap Between Knowledge and Creativitycited by 56
  29. 2024STaRK: Benchmarking LLM Retrieval on Textual and Relational Knowledge Basescited by 55
  30. 2023Joint Bayesian Inference of Graphical Structure and Parameters with a Single Generative Flow Networkcited by 50
  31. 2021Improving Subgraph Recognition with Variational Graph Information Bottleneckcited by 45
  32. 2025VersaPRM: Multi-Domain Process Reward Model via Synthetic Reasoning Datacited by 40
  33. 2023Mind the Label Shift of Augmentation-based Graph OOD Generalizationcited by 34
  34. 2023KnowGPT: Knowledge Graph based Prompting for Large Language Modelscited by 31
  35. 2025RAG-RL: Advancing Retrieval-Augmented Generation via RL and Curriculum Learningcited by 30
  36. 2024HybGRAG: Hybrid Retrieval-Augmented Generation on Textual and Relational Knowledge Basescited by 29
  37. 2024Understand What LLM Needs: Dual Preference Alignment for Retrieval-Augmented Generationcited by 27
  38. 2024Knowledge-Aware Query Expansion with Large Language Models for Textual and Relational Retrievalcited by 26

50 most cited of 66 All 66 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 8.

8 papers.

  1. 2026Autonomous Knowledge Graph Exploration with Adaptive Breadth-Depth Retrievalcited by 3
  2. 2026Calibrated Fusion for Heterogeneous Graph-Vector Retrieval in Multi-Hop QAcited by 2
  3. 2026MemGround: Long-Term Memory Evaluation Kit for Large Language Models in Gamified Scenarioscited by 2
  4. 2026MG2-RAG: Multi-Granularity Graph for Multimodal Retrieval-Augmented Generationcited by 1
  5. 2026HVM-GraphRAG: Holistic-View Multimodal Graph Retrieval-Augmented Generation on Complex Documentcited by 1
  6. 2026SeedER: Seed-Expand-Retrieve for Efficient Knowledge Graph Retrievalcited by 0
  7. 2026TRACE: Trustworthy Retrieval-Augmented Conversational Enginecited by 0
  8. 2026LivingRAG: Augmenting Graph RAG with Experiencecited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025Graph-based Approaches and Functionalities in Retrieval-Augmented Generation: A Comprehensive Survey
  2. 2024Graph Retrieval-Augmented Generation: A Survey
  3. 2025A Survey of Graph Retrieval-Augmented Generation for Customized Large Language Models
  4. 2025NodeRAG: Structuring Graph-based RAG with Heterogeneous Nodes
  5. 2025A Query-Aware Multi-Path Knowledge Graph Fusion Approach for Enhancing Retrieval-Augmented Generation in Large Language Models
  6. 2025Pseudo-Knowledge Graph: Meta-Path Guided Retrieval and In-Graph Text for RAG-Equipped LLM
  7. 2026Use Graph When It Needs: Efficiently and Adaptively Integrating Retrieval-Augmented Generation with Graphs
  8. 2024Simple Is Effective: The Roles of Graphs and Large Language Models in Knowledge-Graph-Based Retrieval-Augmented Generation