How Do LLMs See Charts? A Comparative Study on High-Level Visualization Comprehension in Humans and LLMs
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866908951215341568 |
|---|---|
| author | Jeon, Hyotaek Lee, Hyunwook Shin, Minjeong Pandey, Tapendra Kim, Joohee Seon, Shinwook Jeong, Daeun Ko, Sungahn Quadri, Ghulam Jilani |
| author_facet | Jeon, Hyotaek Lee, Hyunwook Shin, Minjeong Pandey, Tapendra Kim, Joohee Seon, Shinwook Jeong, Daeun Ko, Sungahn Quadri, Ghulam Jilani |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_08959 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | How Do LLMs See Charts? A Comparative Study on High-Level Visualization Comprehension in Humans and LLMs Jeon, Hyotaek Lee, Hyunwook Shin, Minjeong Pandey, Tapendra Kim, Joohee Seon, Shinwook Jeong, Daeun Ko, Sungahn Quadri, Ghulam Jilani Human-Computer Interaction 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. |
| title | How Do LLMs See Charts? A Comparative Study on High-Level Visualization Comprehension in Humans and LLMs |
| topic | Human-Computer Interaction |
| url | https://arxiv.org/abs/2604.08959 |