Graph4LLM: A Systematic Survey of Graph-Enhanced Large Language Models

Zhu, Xinyan; Yang, Cheng; Wang, Qiuyu; Guo, Zeyuan; Wang, Yiding; Liu, Zedi; Wang, Chunchen; Shi, Chuan

doi:10.24963/ijcai.2026/902

Graph4LLM: A Systematic Survey of Graph-Enhanced Large Language Models

Xinyan Zhu, Cheng Yang, Qiuyu Wang, Zeyuan Guo, Yiding Wang, Zedi Liu, Chunchen Wang, Chuan Shi

Download BibTeX Cite

Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence. Survey Track. Pages 8134-8142.

https://doi.org/10.24963/ijcai.2026/902

Keywords

Natural Language Processing: Language models
Data Mining: Mining graphs

Abstract

Large Language Models (LLMs) excel in natural language processing (NLP) tasks. However, they suffer from inherent limitations due to their sequence-based nature, such as structural information loss and factual unreliability. Graphs, with the ability to explicitly model entities and relations, offer an effective way to address these shortcomings. To systematically synthesize the emerging research on graph-enhanced LLMs, this survey, Graph4LLM, examines how these methods integrate graphs into various stages of the LLM pipeline, including the input, model, and output phases. For each phase, we provide a detailed review of the key methods and techniques. We also introduce a wide range of application scenarios where Graph4LLM methods demonstrate significant potential. Finally, we outline the challenges and future research directions for developing more efficient and interpretable solutions.

Xinyan Zhu, Cheng Yang, Qiuyu Wang, Zeyuan Guo, Yiding Wang, Zedi Liu, Chunchen Wang, and Chuan Shi. 2026. Graph4LLM: A Systematic Survey of Graph-Enhanced Large Language Models. In Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence, IJCAI-26. IJCAI, 8134–8142. https://doi.org/10.24963/ijcai.2026/902

@inproceedings{ijcai2026p902,
  title     = {Graph4LLM: A Systematic Survey of Graph-Enhanced Large Language Models},
  author    = {Zhu, Xinyan and Yang, Cheng and Wang, Qiuyu and Guo, Zeyuan and Wang, Yiding and Liu, Zedi and Wang, Chunchen and Shi, Chuan},
  booktitle = {Proceedings of the Thirty-Fifth International Joint Conference on
               Artificial Intelligence, {IJCAI-26}},
  publisher = {International Joint Conferences on Artificial Intelligence Organization},
  editor    = {Diego Calvanese},
  pages     = {8134--8142},
  year      = {2026},
  month     = {8},
  note      = {Survey Track},
  doi       = {10.24963/ijcai.2026/902},
  url       = {https://doi.org/10.24963/ijcai.2026/902},
}

TY  - CPAPER
TI  - Graph4LLM: A Systematic Survey of Graph-Enhanced Large Language Models
AU  - Zhu, Xinyan
AU  - Yang, Cheng
AU  - Wang, Qiuyu
AU  - Guo, Zeyuan
AU  - Wang, Yiding
AU  - Liu, Zedi
AU  - Wang, Chunchen
AU  - Shi, Chuan
T2  - Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence, IJCAI-26
PB  - International Joint Conferences on Artificial Intelligence Organization
PY  - 2026
SP  - 8134
EP  - 8142
DO  - 10.24963/ijcai.2026/902
UR  - https://doi.org/10.24963/ijcai.2026/902
ER  -