mlsanityData to 7 Oct 2026

LLM4DyG: Can Large Language Models Solve Spatial-Temporal Problems on Dynamic Graphs?

arXiv 2310.17110 ↗First posted 26 Oct 2023cs.LGcited by 40

Not on the map. Why?

Abstract (arXiv)

In an era marked by the increasing adoption of Large Language Models (LLMs) for various tasks, there is a growing focus on exploring LLMs' capabilities in handling web data, particularly graph data. Dynamic graphs, which capture temporal network evolution patterns, are ubiquitous in real-world web data. Evaluating LLMs' competence in understanding spatial-temporal information on dynamic graphs is essential for their adoption in web applications, which remains unexplored in the literature. In this paper, we bridge the gap via proposing to evaluate LLMs' spatial-temporal understanding abilities on dynamic graphs, to the best of our knowledge, for the first time. Specifically, we propose the LLM4DyG benchmark, which includes nine specially designed tasks considering the capability evaluation of LLMs from both temporal and spatial dimensions. Then, we conduct extensive experiments to analyze the impacts of different data generators, data statistics, prompting techniques, and LLMs on the model performance. Finally, we propose Disentangled Spatial-Temporal Thoughts (DST2) for LLMs on dynamic graphs to enhance LLMs' spatial-temporal understanding abilities. Our main observations are: 1) LLMs have preliminary spatial-temporal understanding abilities on dynamic graphs, 2) Dynamic graph tasks show increasing difficulties for LLMs as the graph size and density increase, while not sensitive to the time span and data generation mechanism, 3) the proposed DST2 prompting method can help to improve LLMs' spatial-temporal understanding abilities on dynamic graphs for most tasks. The data and codes are publicly available at Github.

Key facts. Cited by 40 papers in the map (data through 7 Oct 2026). Builds on 39 of its 93 references that are in the map. First posted on arXiv 26 Oct 2023.

Builds on

39 of 93 references.

References · 39

  1. 2020Language Models are Few-Shot Learnerscited by 32,199
  2. 2023LLaMA: Open and Efficient Foundation Language Modelscited by 13,958
  3. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,302
  4. 2018How Powerful are Graph Neural Networks?cited by 4,355
  5. 2022Flamingo: a Visual Language Model for Few-Shot Learningcited by 4,337
  6. 2022Large Language Models are Zero-Shot Reasonerscited by 4,323
  7. 2023Qwen Technical Reportcited by 3,273
  8. 2019A Comprehensive Survey on Graph Neural Networkscited by 2,906
  9. 2023A Survey on Large Language Model based Autonomous Agentscited by 2,203
  10. 2023Code Llama: Open Foundation Models for Codecited by 2,105
  11. 2018Graph Neural Networks: A Review of Methods and Applicationscited by 1,571
  12. 2021GLM: General Language Model Pretraining with Autoregressive Blank Infillingcited by 1,026
27 more
  1. 2023Graph of Thoughts: Solving Elaborate Problems with Large Language Modelscited by 873
  2. 2016InfoGAN: Interpretable Representation Learning by Information Maximizing Generative Adversarial Netscited by 858
  3. 2023Multimodal Chain-of-Thought Reasoning in Language Modelscited by 740
  4. 2023Baichuan 2: Open Large-scale Language Modelscited by 664
  5. 2020Temporal Graph Networks for Deep Learning on Dynamic Graphscited by 521
  6. 2020Inductive Representation Learning on Temporal Graphscited by 454
  7. 2023StructGPT: A General Framework for Large Language Model to Reason over Structured Datacited by 339
  8. 2022Teaching Small Language Models to Reasoncited by 279
  9. 2016Structured Sequence Modeling with Graph Convolutional Recurrent Networkscited by 273
  10. 2023Exploring the Potential of Large Language Models (LLMs) in Learning on Graphscited by 271
  11. 2023Can Language Models Solve Graph Problems in Natural Language?cited by 249
  12. 2023Language is All a Graph Needscited by 219
  13. 2021Inductive Representation Learning in Temporal Networks via Causal Anonymous Walkscited by 188
  14. 2023TEST: Text Prototype Aligned Embedding to Activate LLM's Ability for Time Seriescited by 165
  15. 2023What In-Context Learning "Learns" In-Context: Disentangling Task Recognition and Task Learningcited by 149
  16. 2020Foundations and modelling of dynamic networks using Dynamic Graph Neural Networks: A surveycited by 123
  17. 2017Disentangled Person Image Generationcited by 98
  18. 2019Variational Graph Recurrent Neural Networkscited by 86
  19. 2020Factorizable Graph Convolutional Networkscited by 79
  20. 2021Discrete-time Temporal Network Embedding via Implicit Hierarchical Learning in Hyperbolic Spacecited by 67
  21. 2020TeMP: Temporal Message Passing for Temporal Knowledge Graph Completioncited by 61
  22. 2020Structural Temporal Graph Neural Networks for Anomaly Detection in Dynamic Graphscited by 55
  23. 2021Hyperbolic Variational Graph Neural Network for Modeling Dynamic Graphscited by 49
  24. 2019Independence Promoted Graph Disentangled Networkscited by 38
  25. 2019Hierarchical Temporal Convolutional Networks for Dynamic Recommender Systemscited by 28
  26. 2022Learning to Solve Travelling Salesman Problem with Hardness-adaptive Curriculumcited by 27
  27. 2023EasyDGL: Encode, Train and Interpret for Continuous-time Dynamic Graph Learningcited by 7

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 1; 2024: 13; 2025: 17; 2026: 9.

40 papers.

Sort:

By area:

  1. 2023Large Language Models on Graphs: A Comprehensive Surveycited by 190
  2. 2024Demystifying Chains, Trees, and Graphs of Thoughtscited by 63
  3. 2024InstructGraph: Boosting Large Language Models via Graph-centric Instruction Tuning and Preference Alignmentcited by 56
  4. 2025Foundation Models for Spatio-Temporal Data Science: A Tutorial and Surveycited by 23
  5. 2024A survey of dynamic graph neural networkscited by 21
  6. 2025When Do LLMs Help With Node Classification? A Comprehensive Analysiscited by 21
  7. 2024A Survey of Large Language Models on Generative Graph Analytics: Query, Learning, and Applicationscited by 17
  8. 2024GraphEval36K: Benchmarking Coding and Reasoning Capabilities of Large Language Models on Graph Datasetscited by 12
  9. 2024GraphTeam: Facilitating Large Language Model-based Graph Analysis via Multi-Agent Collaborationcited by 12
  10. 2025Graph2text or Graph2token: A Perspective of Large Language Models for Graph Learningcited by 12
  11. 2025Exploring Graph Learning Tasks with Pure LLMs: A Comprehensive Benchmark and Investigationcited by 11
  12. 2024A Survey on Self-Supervised Graph Foundation Models: Knowledge-Based Perspectivecited by 9
28 more
  1. 2025GraphThought: Graph Combinatorial Optimization with Thought Generationcited by 9
  2. 2024Lost-in-Distance: Impact of Contextual Proximity on LLM Performance in Graph Taskscited by 8
  3. 2025Evaluating Large Language Models for Real-World Engineering Taskscited by 7
  4. 2024CodeGraph: Enhancing Graph Reasoning of LLMs with Codecited by 6
  5. 2025Unifying Text Semantics and Graph Structures for Temporal Text-attributed Graphs with Large Language Modelscited by 6
  6. 2024Graph Linearization Methods for Reasoning on Graphs with Large Language Modelscited by 5
  7. 2024Are Large-Language Models Graph Algorithmic Reasoners?cited by 5
  8. 2024How to Make LMs Strong Node Classifiers?cited by 4
  9. 2025A Survey on Temporal Interaction Graph Representation Learning: Progress, Challenges, and Opportunitiescited by 4
  10. 2025IRLBench: A Multi-modal, Culturally Grounded, Parallel Irish-English Benchmark for Open-Ended LLM Reasoning Evaluationcited by 4
  11. 2025LLMTM: Benchmarking and Optimizing LLMs for Temporal Motif Analysis in Dynamic Graphscited by 4
  12. 2025Large Language Models for Cryptocurrency Transaction Analysis: A Bitcoin Case Studycited by 3
  13. 2025Are Large Language Models Good Temporal Graph Learners?cited by 3
  14. 2025Constraint-Aware Route Recommendation from Natural Language via Hierarchical LLM Agentscited by 3
  15. 2024Enhancing ID-based Recommendation with Large Language Modelscited by 2
  16. 2025See or Say Graphs: Agent-Driven Scalable Graph Structure Understanding with Vision-Language Modelscited by 2
  17. 2026GABench: A Comprehensive Benchmark for Evaluating LLM Agents on Graph Analysis Taskscited by 2
  18. 2025Using LLMs for Analyzing AIS Datacited by 1
  19. 2025Self-Exploring Language Models for Explainable Link Forecasting on Temporal Graphs via Reinforcement Learningcited by 1
  20. 2025GLOW: Graph-Language Co-Encoding for Agentic Workflow Performance Predictioncited by 1
  21. 2026Colorful Talks with Graphs: Human-Interpretable Graph Encodings for Large Language Modelscited by 1
  22. 2026TFWaveFormer: Temporal-Frequency Collaborative Multi-level Wavelet Transformer for Dynamic Link Predictioncited by 0
  23. 2026A Unified Graph Language Model for Multi-Domain Multi-Task Graph Alignment Instruction Tuningcited by 0
  24. 2026Linking Scalar-Intensity Language to Structural Polarization with Validated Signed-Network Measurescited by 0
  25. 2026Are Large Language Models Suitable for Graph Computation? Progress and Prospectscited by 0
  26. 2026AdaSTORM: Scaling LLM Reasoning on Dynamic Graphs via Adaptive Spatio-Temporal Multi-Agent Collaborationcited by 0
  27. 2026GTA: Graph Theory Agent and Benchmark for Algorithmic Graph Reasoning with LLMscited by 0
  28. 2026LLM4Trust: Exploring the Capabilities of Large Language Models for Trust Evaluationcited by 0