LLMs for Graph Learning

LLM: Large Language Model

This field studies how large language models can learn from and reason about graphs, including text-attributed networks, knowledge graphs, molecules, and evolving graphs. Common tasks include node and link prediction, graph classification, anomaly detection, knowledge graph completion, and graph question answering. Approaches serialize graph neighborhoods as text, add graph-aware tokens or attention, combine LLMs with graph neural networks, or use prompting, fine-tuning, distillation, and agents to guide graph exploration. Models can benefit from rich textual knowledge and scarce labels, but benchmarks and analyses show that they may fail to use topology reliably, especially on large or exact graph tasks; balancing semantic reasoning, structural fidelity, and efficient inference remains an open challenge.

Latest papers

74 papers8 papers in the last four weeks, down 27% on the four weeks before. 0.0% of all new papers.

LLM-Enhanced Heterogeneous Graph Learning with Business Semantics for Financial Fraud Detection
Oct 26, 2026Yixuan Chen, Hongyu Zhan, Jie Sheng +5Financial Fraud Detection Heterogeneous GNNs
HKUST-GZ & Jilin University · The Hong Kong University of Science and Technology (Guangzhou) · Ant International +1
Towards a Learnable Retriever for Textual Graph Question Answering
Oct 24, 2026Kaifeng Jin, Yuchen Yan, Zhichen Zeng +4Graph-Based Retrieval Graph Retrieval-Augmented Generation
University of Illinois Urbana-Champaign · Wayne State University · Meta
Big Claims, Small Margins: Do Reported GraphLLM Gains Survive Simple Baselines?
Oct 20, 2026Michal PodstawskiLLMs for Graph Learning Text-Attributed Graph Learning
NASK National Research Institute, Warsaw, Poland.
Uncovering Semantic Hierarchies in Text-Attributed Graphs via Variational EM-based LLM-GNN Synergy
Oct 17, 2026Yunhui Liu, Xudong Jin, Qizhuo Xie +5Text-Attributed Graph Learning Hierarchical Representation Learning
State Key Laboratory for Novel Software Technology, Nanjing University · Department of Statistics, University of Wisconsin–Madison · National Engineering Laboratory for Big Data Analysis and Applications, Peking University
S-GAP: Stealthy Graph Attack Primitives for Graph Large Language Models
Oct 16, 2026Wenda Li, Tongya Zheng, Shunyu Liu +8Adversarial Attacks on LLMs LLMs for Graph Learning
1Zhejiang University · 2Hangzhou City University · 3Nanyang Technological University +1
FRACTION: Fraud Explanation Generation via Agentic Graph Context Navigation
Oct 13, 2026Cecelia Soh, Jun Hu, Yuan Li +6Faithfulness of Language Model Explanations LLMs for Graph Learning
National University of Singapore · Hefei University of Technology · ByteDance Inc. +1
Overcoming Challenges of Interpretive Structural Modeling with Large Language Models
Sep 30, 2026Everett Rush, David J. Icove, Ari Kim +2Multi-Criteria Decision Analysis Causal Discovery
Department of Electrical Engineering and Computer Science, University of Tennessee, Knoxville, TN · Oak Ridge National Laboratory, Oak Ridge, TN
GraphMAS: A Systematic Benchmark of Multi-Agent Coordination for Graph Learning
Sep 30, 2026Jiayi Yang, Yifang Chen, Yuanfu Sun +2Multi-Agent Coordination Text-Attributed Graph Learning
New York University Shanghai · New York University · Northwestern University
A Spectral Theory of Distortion in LLM Graph Reconstruction: Sharp Bounds and Empirical Characterization
Sep 29, 2026Jianru ShenLLMs for Graph Learning Wasserstein Distance
Columbia University New York, NY, USA
ZeroGAR: Benchmarking the Adversarial Robustness of Zero-Shot Graph Models
Sep 27, 2026Zhongjian Zhang, Xiao Wang, Busheng Zhang +5Graph Representation Learning Adversarial Attacks
Beijing University of Posts and Telecommunications · Beihang University · Tsinghua University +2
TemporalGraphLLM: Temporal Graph Neural Networks with Large Language Models for Dynamic Text-Attributed Graphs
Sep 25, 2026Moran Beladev, Or Eitan, Gilad Katz +1Text-Attributed Graph Learning LLMs for Graph Learning
Department of Information Systems Engineering Ben-Gurion University of the Negev, Israel
ABSOL: Aggregated Bayesian Subsampling Orchestrated with LLMs
Sep 14, 2026Jackson Hassell, Chen Shen, Estevam HruschkaGraph Structure Learning Bayesian Network Structure Learning
Megagon Labs
Structurally Speaking: Motif-Oriented Graph Captioning through Bidirectional Graph-Text Translation
Sep 10, 2026Hsiao-Ying Lu, Dongyu Liu, Kwan-Liu MaStructured Prompting Graph Reconstruction
Department of Computer Science, University of California, Davis
Chimaera: A Mixture-of-Graph-Experts Architecture for Cross-Task and Cross-Dataset Graph Learning
Sep 8, 2026Jonatan Frank, David Richerby, Ansgar ScherpTransfer Learning Text-Attributed Graph Learning
University of Ulm, Ulm, Germany · University of Essex, Colchester, UK
TTGBench: Benchmarking Topological Evolution and Semantic Drift in Text-attributed Temporal Graphs
Sep 8, 2026Longfei Ma, Zemin Liu, Fei WuTemporal GNNs Semantic Drift in Language Models
1Zhejiang University
LLMs for Social Network Modeling: From Network Generation to Dynamic Processes
Sep 7, 2026Shikha Mallick, Alex Thomo, Akrati SaxenaComputational Social Science LLMs for Graph Learning
Department of Computer Science, University of Victoria, BC, Canada · Leiden Institute of Advanced Computer Science, Leiden University, The Netherlands
REFINE: LLM Refinement over Budgeted Text-Attributed Graphs for Personalized Medical Concept Representation
Sep 3, 2026Mohsen Nayebi Kerdabadi, Arya Hadizadeh Moghaddam, Dongjie Wang +1Text-Attributed Graph Learning LLMs for Graph Learning
University of Kansas, USA
Language-encoded network topology enables large language models to reason about complex networks
Sep 3, 2026Ucchwas Talukder Utsha, Sakib Mostafa, James Zou +1Graph Representation Learning LLM Reasoning with Graphs
Department of Radiation Oncology, Stanford University, Stanford, California, USA · Department of Electrical Engineering, Stanford University, Stanford, California, USA · Department of Biomedical Data Science, Stanford University School of Medicine, Stanford, California, USA +1
CoMPASS: Collaborative Molecular Property Prediction via Adaptive Small-Large Model Synergy
Aug 31, 2026Wentao Li, Jiangjie Qiu, Yijun Li +2Graph Neural Networks Language Model Calibration
Beijing Key Laboratory of Artificial Intelligence for Advanced Chemical Engineering Materials · State Key Laboratory of Chemical Engineering and Low-Carbon Technology · Department of Chemical Engineering, Tsinghua University
Graph Evidence Is Not Enough: Diagnosing Native Decoder Use in Graph-Augmented LLMs
Aug 31, 2026Xiaoyu Guo, Pengcheng Chen, Jiong Yu +3LLM Reasoning with Graphs LLM Reasoning
School of Software, Xinjiang University, Urumqi 830002, China · School of Computer Science and Technology, Xinjiang University, Urumqi 830046, China
Why Does Graph Learning Fail to Fully Benefit from a Text Teacher?
Aug 26, 2026Fumiaki Kimino, Ryoma SatoGraph Representation Learning Text-Attributed Graph Learning
SOKENDAI · National Institute of Informatics · National Institute of Informatics, SOKENDAI
Auditing Privacy Risks in LLM-Enhanced Graph Neural Networks
Aug 26, 2026Longzhu He, Zelang Wen, Chaozhuo Li +1Privacy-Preserving ML LLMs for Graph Learning
Beijing University of Posts and Telecommunications
Who Should Teach? Confidence-Aware Dual-Teacher Learning for Few-Shot Node Classification on Text-Attributed Graphs
Aug 22, 2026Hojin Kim, Sujin Yoon, Sungsu Lim +2Text-Attributed Graph Learning Node Classification
Chungbuk National University Cheongju, South Korea · Chungnam National University Daejeon, South Korea · The Pennsylvania State University University Park, PA, USA
TAHB: A Comprehensive Benchmark for Text-Attributed Hypergraph Learning
Aug 15, 2026David Yoon Suk Kang, JungHyun Kim, Juhyun Jeon +1Hypergraph Learning LLMs for Graph Learning
Chungbuk National University South Korea · Hanyang University South Korea
Multi-Granular Rationale-Guided Molecular LLM for Property Prediction
Aug 11, 2026Junwoo Park, Minyoung Shin, Cheol Soon Lee +1Molecular Property Prediction Molecular Representation Learning
Sungkyunkwan University · Korea University
Unified Multi-Dimensional Benchmark for Complex Graph Reasoning in Large Language Models
Aug 2, 2026Fali Wang, Ali Al-Lawati, Iliyas Bektas +5LLM Evaluation LLM Reasoning with Graphs
The Pennsylvania State University, University Park, PA, USA · Rensselaer Polytechnic Institute, Troy, NY, US
Interpretable Unsupervised Community Detection with LLM-Symbolized Structured Processes
Aug 2, 2026Aoting Zeng, Kai Wang, Jianwei Wang +3Unsupervised Learning Interpretable ML
Shanghai Jiao Tong University Shanghai, China · University of New South Wales Sydney, Australia
Agentic Graph Token Reasoning
Aug 1, 2026Zhuoyi Peng, Yi YangLLM Reasoning with Graphs Text-Attributed Graph Learning
The Hong Kong University of Science and Technology
Dual-Path LLM Reasoning for Multimodal Few-Shot Knowledge Graph Completion
Jul 29, 2026Jinlan Liu, Zhiying Tu, Yongchao Xing +5Multimodal Graph Learning Multimodal KGs
Harbin Institute of Technology (Weihai), Weihai 264209, China · Shandong Provincial Key Laboratory of Digital Service Computing Technology and Systems, Weihai 264200, China · Harbin Institute of Technology Qingdao Research Institute, Qingdao 266400, China
CHARM: A Multimodal Graph Foundation Model with Hierarchical Context Modeling for Zero-Shot Transfer
Jul 28, 2026Ankang Yang, Jitao Zhao, Di Jin +2Transfer Learning Graph Foundation Models
School of Computer Science and Technology, College of Intelligence and Computing, Tianjin University · Data Science Program, Columbian College of Arts and Sciences, The George Washington University

Oct 26, 2026J/K move · Enter open · S save

LLM-Enhanced Heterogeneous Graph Learning with Business Semantics for Financial Fraud Detection

Yixuan Chen, Hongyu Zhan, Jie Sheng, Weiyu Han+4

HKUST-GZ & Jilin University · The Hong Kong University of Science and Technology (Guangzhou) · Ant International+1

Financial Fraud Detection Heterogeneous GNNs LLMs for Graph Learning Large Language Model-Based Feature Engineering

Open paper AskPDF arXiv

Financial fraud detection increasingly relies on heterogeneous transaction graphs, in which entities such as cards and merchants play distinct business roles and the risk meaning of an attribute depends on the entity's role: a high transaction volume may be routine for a merchant but unusual for a card. Heterogeneous graph neural networks preserve typed entities and relations but typically treat these attributes as role-agnostic inputs and leave their business meaning implicit. Meanwhile, most existing methods integrating large language models (LLMs) with graphs focus on homogeneous graphs or heterogeneous graphs with naturally available textual attributes, leaving their use on transaction graphs with structured attributes underexplored. To address this issue, we propose SemHGT, an LLM-enhanced framework that interprets structured attributes according to entity roles and makes the business semantics explicit in three stages: (1) role-aware prompts elicit risk-related business descriptions from node attributes, and a text encoder maps them to semantic vectors that enrich node representations; (2) semantic similarity guides multi-round sampling of target-specific path instances under transaction-to-transaction schemas; (3) schema-level tokens that combine local path evidence with global neighbor summaries are processed together with the target transaction by a unified transformer. Across three benchmark datasets, SemHGT leads the evaluated baselines on most dataset--metric comparisons. Further analyses provide additional evidence for the effectiveness of SemHGT's design and clarify how its semantic modeling and evidence selection contribute to fraud detection. Code is available at https://anonymous.4open.science/r/SemHGT-528A/.