Saved in:
| Main Author: | |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2602.23746 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866918359512121344 |
|---|---|
| author | Haraguchi, Daichi |
| author_facet | Haraguchi, Daichi |
| contents | High text recognition performance does not guarantee that Vision-Language Models (VLMs) share human-like decision patterns when resolving ambiguity. We investigate this behavioral gap by directly comparing humans and VLMs using continuously interpolated Japanese character shapes generated via a $β$-VAE. We estimate decision boundaries in a single-character recognition (shape-only task) and evaluate whether VLM responses align with human judgments under shape in context (i.e., embedding an ambiguous character near the human decision boundary in word-level context). We find that human and VLM decision boundaries differ in the shape-only task, and that shape in context can improve human alignment in some conditions. These results highlight qualitative behavioral differences, offering foundational insights toward human--VLM alignment benchmarking. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_23746 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Shape vs. Context: Examining Human--AI Gaps in Ambiguous Japanese Character Recognition Haraguchi, Daichi Human-Computer Interaction Computer Vision and Pattern Recognition High text recognition performance does not guarantee that Vision-Language Models (VLMs) share human-like decision patterns when resolving ambiguity. We investigate this behavioral gap by directly comparing humans and VLMs using continuously interpolated Japanese character shapes generated via a $β$-VAE. We estimate decision boundaries in a single-character recognition (shape-only task) and evaluate whether VLM responses align with human judgments under shape in context (i.e., embedding an ambiguous character near the human decision boundary in word-level context). We find that human and VLM decision boundaries differ in the shape-only task, and that shape in context can improve human alignment in some conditions. These results highlight qualitative behavioral differences, offering foundational insights toward human--VLM alignment benchmarking. |
| title | Shape vs. Context: Examining Human--AI Gaps in Ambiguous Japanese Character Recognition |
| topic | Human-Computer Interaction Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2602.23746 |