How Do LLMs See Charts? A Comparative Study on High-Level Visualization Comprehension in Humans and LLMs

TL;DR

This study compares how humans and large language models interpret high-level visualizations, revealing differences in reasoning strategies and highlighting challenges for visualization design.

Contribution

It provides a qualitative analysis of LLMs' visualization comprehension, contrasting their reasoning with human interpretative strategies across different visualization types.

Findings

LLMs show consistent interpretative strategies across prompt conditions.

Humans synthesize data into trend-centric narratives.

LLMs rely on structural enumeration and numerical comparisons.

Abstract

Designers often create visualizations to achieve specific high-level analytical or communication goals. These goals require people to extract complex and interconnected data patterns. Prior perceptual studies of visualization effectiveness have focused on low-level tasks, such as estimating statistical quantities, and have recently explored high-level comprehension of visualization. Despite the growing use of Large Language Models (LLMs) as visualization interpreters, how their interpretations relate to human understanding or what reasoning processes underlie their responses remains insufficiently understood. In this work, we explore LLMs' visualization comprehension, examining the alignment between designers' communicative goals and what their audience sees in a visualization. We have conducted a qualitative study to investigate the gap between human interpretative strategies and the reasoning pathways of LLMs across three types of visualizations, line graphs, bar graphs, and scatterplots, to identify the high-level patterns generated by LLMs using three prompt conditions. Our analysis results indicate that LLMs exhibit a consistent interpretative strategy that remains unchanged across prompt constraints. Furthermore, we observe two distinct approaches: humans naturally synthesize data into trend-centric narratives, whereas LLMs persist with a structural enumeration of comparisons and numerical ranges. Lastly, we see LLMs achieve visualization comprehension through mechanisms distinct from human intuition, pointing to critical challenges and new opportunities for visualization design.