Graph Drawing for LLMs: An Empirical Evaluation
This work addresses the problem of optimizing visual inputs for LLMs in graph analysis, which is incremental to existing research on LLM-based graph tasks.
The paper investigates how visual graph drawings affect Large Language Model performance on graph-related tasks, finding that layout choice and drawing readability significantly improve results, while effective prompting is crucial but challenging.
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.