Nodes Are Early, Edges Are Late: Probing Diagram Representations in Large Vision-Language Models

TL;DR

This paper investigates why large vision-language models struggle with understanding relationships in diagrams, revealing that edge information is encoded later in the processing pipeline than node information.

Contribution

The study uncovers the stage at which different diagram elements are linearly encoded in LVLMs, highlighting the delayed encoding of edge information compared to nodes.

Findings

Edge information is not linearly separable in the vision encoder.

Node information is linearly encoded in the vision encoder.

Edge representations emerge later in the processing pipeline.

Abstract

Large vision-language models (LVLMs) demonstrate strong performance on diagram understanding benchmarks, yet they still struggle with understanding relationships between elements, particularly those represented by nodes and directed edges (e.g., arrows and lines). To investigate the underlying causes of this limitation, we probe the internal representation of LVLMs using a carefully constructed synthetic diagram dataset based on directed graphs. Our probing experiments reveal that edge information is not linearly separable in the vision encoder and becomes linearly encoded only in the text tokens in the language model. In contrast, node information and global structural features are already linearly encoded in individual hidden states of the vision encoder. These findings suggest that the stage at which linearly separable representations are formed varies depending on the type of visual information. In particular, the delayed emergence of edge representations may help explain why LVLMs struggle with relational understanding, such as interpreting edge directions, which require more abstract, compositionally integrated processes.