Exploring Graph Structure Comprehension Ability of Multimodal Large Language Models: Case Studies
It addresses the problem of improving graph understanding for AI researchers by exploring incremental enhancements through visual modalities.
This study investigated how multimodal large language models (LLMs) that process both text and images perform on graph comprehension tasks compared to purely textual representations, finding insights into their potential and limitations.
Large Language Models (LLMs) have shown remarkable capabilities in processing various data structures, including graphs. While previous research has focused on developing textual encoding methods for graph representation, the emergence of multimodal LLMs presents a new frontier for graph comprehension. These advanced models, capable of processing both text and images, offer potential improvements in graph understanding by incorporating visual representations alongside traditional textual data. This study investigates the impact of graph visualisations on LLM performance across a range of benchmark tasks at node, edge, and graph levels. Our experiments compare the effectiveness of multimodal approaches against purely textual graph representations. The results provide valuable insights into both the potential and limitations of leveraging visual graph modalities to enhance LLMs' graph structure comprehension abilities.