|国家预印本平台
首页|Graph Drawing for LLMs: An Empirical Evaluation

Graph Drawing for LLMs: An Empirical Evaluation

Graph Drawing for LLMs: An Empirical Evaluation

来源:Arxiv_logoArxiv
英文摘要

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.

Walter Didimo、Fabrizio Montecchiani、Tommaso Piselli

计算技术、计算机技术

Walter Didimo,Fabrizio Montecchiani,Tommaso Piselli.Graph Drawing for LLMs: An Empirical Evaluation[EB/OL].(2025-05-06)[2025-06-06].https://arxiv.org/abs/2505.03678.点此复制

评论