mlsanityData to 7 Oct 2026

KGFR: A Foundation Retriever for Generalized Knowledge Graph Question Answering

arXiv 2511.04093 ↗First posted 6 Nov 2025cs.AIcited by 0

On the map: LLM reasoning → Knowledge- and tool-augmented reasoning

Abstract (arXiv)

Large language models (LLMs) excel at reasoning but struggle with knowledge-intensive questions due to limited context and parametric knowledge. However, existing methods that rely on finetuned LLMs or GNN retrievers are limited by dataset-specific tuning and scalability on large or unseen graphs. We propose the LLM-KGFR collaborative framework, where an LLM works with a structured retriever, the Knowledge Graph Foundation Retriever (KGFR). KGFR encodes relations using LLM-generated descriptions and initializes entities based on their roles in the question, enabling zero-shot generalization to unseen KGs. To handle large graphs efficiently, it employs Asymmetric Progressive Propagation (APP)- a stepwise expansion that selectively limits high-degree nodes while retaining informative paths. Through node-, edge-, and path-level interfaces, the LLM iteratively requests candidate answers, supporting facts, and reasoning paths, forming a controllable reasoning loop. Experiments demonstrate that LLM-KGFR achieves strong performance while maintaining scalability and generalization, providing a practical solution for KG-augmented reasoning.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Placed in Knowledge- and tool-augmented reasoning, one of 17 directions in LLM reasoning. Builds on 65 of its 81 references that are in the map. First posted on arXiv 6 Nov 2025.

Builds on

65 of 81 references.

Closest ancestors · 8

Same direction, newest first

  1. 2025LightPROF: A Lightweight Reasoning Framework for Large Language Model on Knowledge Graph4 Apr
  2. 2024Plan-on-Graph: Self-Correcting Adaptive Planning of Large Language Model on Knowledge Graphs31 Oct
  3. 2024Graph-constrained Reasoning: Faithful Reasoning on Knowledge Graphs with Large Language Models16 Oct
  4. 2024GNN-RAG: Graph Neural Retrieval for Large Language Model Reasoning30 May
  5. 2023Reasoning on Graphs: Faithful and Interpretable Large Language Model Reasoning2 Oct
  6. 2023Can Language Models Solve Graph Problems in Natural Language?17 May
  7. 2023GrapeQA: GRaph Augmentation and Pruning to Enhance Question-Answering22 Mar
  8. 2022UniKGQA: Unified Retrieval and Reasoning for Solving Multi-hop Question Answering Over Knowledge Graph2 Dec

Other references · 57

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  2. 2022Large Language Models are Zero-Shot Reasonerscited by 4,323
  3. 2018Can a Suit of Armor Conduct Electricity? A New Dataset for Open Book Question Answeringcited by 2,114
  4. 2018CommonsenseQA: A Question Answering Challenge Targeting Commonsense Knowledgecited by 1,793
  5. 2023A Survey on Hallucination in Large Language Models: Principles, Taxonomy, Challenges, and Open Questionscited by 1,582
  6. 2024From Local to Global: A Graph RAG Approach to Query-Focused Summarizationcited by 1,411
  7. 2020What Disease does this Patient Have? A Large-scale Open Domain Question Answering Dataset from Medical Examscited by 1,324
  8. 2018Deep Graph Infomaxcited by 1,101
  9. 2016ConceptNet 5.5: An Open Multilingual Graph of General Knowledgecited by 1,065
  10. 2019Strategies for Pre-training Graph Neural Networkscited by 964
  11. 2023Unifying Large Language Models and Knowledge Graphs: A Roadmapcited by 663
  12. 2022GraphMAE: Self-Supervised Masked Graph Autoencoderscited by 443
38 more
  1. 2019InfoGraph: Unsupervised and Semi-supervised Graph-Level Representation Learning via Mutual Information Maximizationcited by 441
  2. 2018The Web as a Knowledge-base for Answering Complex Questionscited by 409
  3. 2021QA-GNN: Reasoning with Language Models and Knowledge Graphs for Question Answeringcited by 386
  4. 2020AmbigQA: Answering Ambiguous Open-domain Questionscited by 385
  5. 2023StructGPT: A General Framework for Large Language Model to Reason over Structured Datacited by 339
  6. 2024LightRAG: Simple and Fast Retrieval-Augmented Generationcited by 310
  7. 2021Neural Bellman-Ford Networks: A General Graph Neural Network Framework for Link Predictioncited by 273
  8. 2024HippoRAG: Neurobiologically Inspired Long-Term Memory for Large Language Modelscited by 273
  9. 2016Key-Value Memory Networks for Directly Reading Documentscited by 223
  10. 2024G-Retriever: Retrieval-Augmented Generation for Textual Graph Understanding and Question Answeringcited by 217
  11. 2019KagNet: Knowledge-Aware Graph Networks for Commonsense Reasoningcited by 216
  12. 2019PullNet: Open Domain Question Answering with Iterative Retrieval on Knowledge Bases and Textcited by 182
  13. 2020Beyond I.I.D.: Three Levels of Generalization for Question Answering on Knowledge Basescited by 169
  14. 2018Open Domain Question Answering Using Early Fusion of Knowledge Bases and Textcited by 167
  15. 2023GraphPrompt: Unifying Pre-Training and Downstream Tasks for Graph Neural Networkscited by 166
  16. 2022Deep Bidirectional Language-Knowledge Graph Pretrainingcited by 156
  17. 2018Canonical Tensor Decomposition for Knowledge Base Completioncited by 150
  18. 2023All in One: Multi-task Prompting for Graph Neural Networkscited by 147
  19. 2024Let Your Graph Do the Talking: Encoding Structured Data for LLMscited by 112
  20. 2021Improving Multi-hop Knowledge Base Question Answering by Learning Intermediate Supervision Signalscited by 100
  21. 2023Knowledge-Driven CoT: Exploring Faithful Reasoning in LLMs for Knowledge-intensive Question Answeringcited by 97
  22. 2022Subgraph Retrieval Enhanced Model for Multi-hop Knowledge Base Question Answeringcited by 93
  23. 2021Knowledge Graph Reasoning with Relational Digraphcited by 91
  24. 2023Towards Foundation Models for Knowledge Graph Reasoningcited by 83
  25. 2023Few-shot In-context Learning for Knowledge Base Question Answeringcited by 74
  26. 2023Graph Neural Prompting with Large Language Modelscited by 64
  27. 2023Graph Prompt Learning: A Comprehensive Survey and Beyondcited by 61
  28. 2021TransferNet: An Effective and Transparent Framework for Multi-hop Question Answering over Relation Graphcited by 60
  29. 2021ExplaGraphs: An Explanation Graph Generation Task for Structured Commonsense Reasoningcited by 58
  30. 2021Complex Knowledge Base Question Answering: A Surveycited by 52
  31. 2025GFM-RAG: Graph Foundation Model for Retrieval Augmented Generationcited by 40
  32. 2023SGL-PT: A Strong Graph Learner with Graph Prompt Tuningcited by 35
  33. 2020Fusing Context Into Knowledge Graph for Commonsense Question Answeringcited by 33
  34. 2023HetGPT: Harnessing the Power of Prompt Tuning in Pre-Trained Heterogeneous Graph Neural Networkscited by 32
  35. 2018AceKG: A Large-scale Knowledge Graph for Academic Data Miningcited by 28
  36. 2021LargeEA: Aligning Entities for Large-scale Knowledge Graphscited by 26
  37. 2024A Prompt-Based Knowledge Graph Foundation Model for Universal In-Context Reasoningcited by 25
  38. 2025TRIX: A More Expressive Model for Zero-shot Domain Transfer in Knowledge Graphscited by 23

50 most cited of 57 All 57 (JSON)

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025Learning Efficient and Generalizable Graph Retriever for Knowledge-Graph Question Answering
  2. 2023KnowledgeNavigator: Leveraging Large Language Models for Enhanced Reasoning over Knowledge Graph
  3. 2025RJE: A Retrieval-Judgment-Exploration Framework for Efficient Knowledge Graph Question Answering with LLMs
  4. 2026The Graph Language: How Knowledge Graphs Speak to Large Language Models
  5. 2026RouterKGQA: Specialized--General Model Routing for Constraint-Aware Knowledge Graph Question Answering
  6. 2026A Human-in-the-Loop, LLM-Centered Architecture for Knowledge-Graph Question Answering
  7. 2024KARPA: A Training-free Method of Adapting Knowledge Graph as References for Large Language Model's Reasoning Path Aggregation
  8. 2024Decoding on Graphs: Faithful and Sound Reasoning on Knowledge Graphs through Generation of Well-Formed Chains