Graph Drawing for LLMs: An Empirical Evaluation
Not on the map. Why?
Abstract (arXiv)
Our work contributes to the fast-growing literature on the use of Large Language Models (LLMs) to perform graph-related tasks. In particular, we focus on usage scenarios that rely on the visual modality, feeding the model with a drawing of the graph under analysis. We investigate how the model's performance is affected by the chosen layout paradigm, the aesthetics of the drawing, and the prompting technique used for the queries. We formulate three corresponding research questions and present the results of a thorough experimental analysis. Our findings reveal that choosing the right layout paradigm and optimizing the readability of the input drawing from a human perspective can significantly improve the performance of the model on the given task. Moreover, selecting the most effective prompting technique is a challenging yet crucial task for achieving optimal performance.
Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Builds on 17 of its 35 references that are in the map. First posted on arXiv 6 May 2025.
Builds on
17 of 35 references.
References · 17
- 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,459
- 2024GPT-4o System Cardcited by 4,588
- 2023A Survey of Large Language Modelscited by 2,576
- 2023A Survey on Hallucination in Large Language Models: Principles, Taxonomy, Challenges, and Open Questionscited by 1,601
- 2024A Systematic Survey of Prompt Engineering in Large Language Models: Techniques and Applicationscited by 431
- 2024LiveBench: A Challenging, Contamination-Limited LLM Benchmarkcited by 262
- 2023GraphGPT: Graph Instruction Tuning for Large Language Modelscited by 226
- 2023GPT4Graph: Can Large Language Models Understand Graph Structured Data ? An Empirical Evaluation and Benchmarkingcited by 210
- 2023Large Language Models on Graphs: A Comprehensive Surveycited by 192
- 2023Talk like a Graph: Encoding Graphs for Large Language Modelscited by 176
- 2021Graph Learning: A Surveycited by 141
- 2023GraphLLM: Boosting Graph Reasoning Ability of Large Language Modelcited by 107
5 more
- 2024A Survey of Large Language Models for Graphscited by 72
- 2024GraphInstruct: Empowering Large Language Models with Graph Understanding and Reasoning Capabilitycited by 58
- 2024GITA: Graph to Visual and Textual Integration for Vision-Language Graph Reasoningcited by 33
- 2023Which Modality should I use -- Text, Motif, or Image? : Understanding Graphs with Large Language Modelscited by 15
- 2021Edge-Path Bundling: A Less Ambiguous Edge Bundling Approachcited by 3
Built on by
Citing papers per year: 2026: 2.
2 papers.