mlsanityData to 7 Oct 2026

The Graph Language: How Knowledge Graphs Speak to Large Language Models

arXiv 2608.01175 ↗First posted 2 Aug 2026cs.AIcited by 0

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

Abstract (arXiv)

Large Language Models (LLMs) excel at reasoning but benefit from grounding provided by Knowledge Graphs (KGs). However, integrating these paradigms is challenging. We introduce GRALAN, which enables KGs to speak directly in the LLM's semantic space through relational tokens that preserve graph structure. GRALAN-s trainable language mediator generates structured tokens for any frozen LLM, creating a foundation for knowledge-intensive applications. We demonstrate its effectiveness in question-answering by re-framing the task as entity classification over question-focused subgraphs. Experiments show that GRALAN significantly outperforms existing methods, particularly on complex multi-hop reasoning tasks, establishing a new paradigm for KG-LLM integration that maintains structural fidelity while leveraging LLMs' reasoning capabilities.

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 43 of its 48 references that are in the map. First posted on arXiv 2 Aug 2026.

Builds on

43 of 48 references.

Closest ancestors · 4

Same direction, newest first

  1. 2023GraphLLM: Boosting Graph Reasoning Ability of Large Language Model9 Oct
  2. 2022UniKGQA: Unified Retrieval and Reasoning for Solving Multi-hop Question Answering Over Knowledge Graph2 Dec
  3. 2022QAGCN: Answering Multi-Relation Questions via Single-Step Implicit Reasoning over Knowledge Graphs3 Jun
  4. 2022GreaseLM: Graph REASoning Enhanced Language Models for Question Answering21 Jan

Other references · 39

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  2. 2020Language Models are Few-Shot Learnerscited by 32,199
  3. 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,491
  4. 2021LoRA: Low-Rank Adaptation of Large Language Modelscited by 14,084
  5. 2018Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challengecited by 4,710
  6. 2021The Power of Scale for Parameter-Efficient Prompt Tuningcited by 3,769
  7. 2019PIQA: Reasoning about Physical Commonsense in Natural Languagecited by 2,818
  8. 2023A Survey of Large Language Modelscited by 2,537
  9. 2018Can a Suit of Armor Conduct Electricity? A New Dataset for Open Book Question Answeringcited by 2,114
  10. 2022Survey of Hallucination in Natural Language Generationcited by 2,056
  11. 2017Modeling Relational Data with Graph Convolutional Networkscited by 1,684
  12. 2021Calibrate Before Use: Improving Few-Shot Performance of Language Modelscited by 1,371
27 more
  1. 2016ConceptNet 5.5: An Open Multilingual Graph of General Knowledgecited by 1,065
  2. 2023A Multitask, Multilingual, Multimodal Evaluation of ChatGPT on Reasoning, Hallucination, and Interactivitycited by 888
  3. 2020KILT: a Benchmark for Knowledge Intensive Language Taskscited by 571
  4. 2018The Web as a Knowledge-base for Answering Complex Questionscited by 409
  5. 2019KEPLER: A Unified Model for Knowledge Embedding and Pre-trained Language Representationcited by 356
  6. 2021ERNIE 3.0: Large-scale Knowledge Enhanced Pre-training for Language Understanding and Generationcited by 258
  7. 2016Key-Value Memory Networks for Directly Reading Documentscited by 223
  8. 2023GraphGPT: Graph Instruction Tuning for Large Language Modelscited by 223
  9. 2023Language is All a Graph Needscited by 219
  10. 2024G-Retriever: Retrieval-Augmented Generation for Textual Graph Understanding and Question Answeringcited by 217
  11. 2022LinkBERT: Pretraining Language Models with Document Linkscited by 209
  12. 2023Talk like a Graph: Encoding Graphs for Large Language Modelscited by 175
  13. 2017Variational Reasoning for Question Answering with Knowledge Graphcited by 170
  14. 2017Go for a Walk and Arrive at the Answer: Reasoning Over Paths in Knowledge Bases using Reinforcement Learningcited by 161
  15. 2023Exploring the Limits of ChatGPT for Query or Aspect-based Text Summarizationcited by 122
  16. 2021Improving Multi-hop Knowledge Base Question Answering by Learning Intermediate Supervision Signalscited by 100
  17. 2021Can Language Models be Biomedical Knowledge Bases?cited by 83
  18. 2020JAKET: Joint Pre-training of Knowledge Graph and Language Understandingcited by 73
  19. 2023Graph Neural Prompting with Large Language Modelscited by 64
  20. 2021RiddleSense: Reasoning about Riddle Questions Featuring Linguistic Creativity and Commonsense Knowledgecited by 60
  21. 2021TransferNet: An Effective and Transparent Framework for Multi-hop Question Answering over Relation Graphcited by 60
  22. 2022Graph Pooling for Graph Neural Networks: Progress, Challenges, and Opportunitiescited by 52
  23. 2018An Interpretable Reasoning Network for Multi-Relation Question Answeringcited by 47
  24. 2024HiGPT: Heterogeneous Graph Language Modelcited by 44
  25. 2020Structured Attention for Unsupervised Dialogue Structure Inductioncited by 19
  26. 2024Question-guided Knowledge Graph Re-scoring and Injection for Knowledge Graph Question Answeringcited by 13
  27. 2023GraphextQA: A Benchmark for Evaluating Graph-Enhanced Large Language Modelscited by 2

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2024Paths-over-Graph: Knowledge Graph Empowered Large Language Model Reasoning
  2. 2025KG-o1: Enhancing Multi-hop Question Answering in Large Language Models via Knowledge Graph Integration
  3. 2024Graph Chain-of-Thought: Augmenting Large Language Models by Reasoning on Graphs
  4. 2025KGFR: A Foundation Retriever for Generalized Knowledge Graph Question Answering
  5. 2025Reasoning with Graphs: Structuring Implicit Knowledge to Enhance LLMs Reasoning
  6. 2025Grounding LLM Reasoning with Knowledge Graphs
  7. 2024Graph-constrained Reasoning: Faithful Reasoning on Knowledge Graphs with Large Language Models
  8. 2025Inference Scaled GraphRAG: Improving Multi Hop Question Answering on Knowledge Graphs