With the widespread adoption of large vision-language models, the capacity for color vision in these models is crucial. However, the color vision abilities of large visual-language models have not yet been thoroughly explored. To address this gap, we define a color vision testing task for large vision-language models and construct a dataset \footnote{Anonymous Github Showing some of the data https://anonymous.4open.science/r/color-vision-test-dataset-3BCD} that covers multiple categories of test questions and tasks of varying difficulty levels. Furthermore, we analyze the types of errors made by large vision-language models and propose fine-tuning strategies to enhance their performance in color vision tests.
@article{arxiv.2507.11153,
title = {Assessing Color Vision Test in Large Vision-language Models},
author = {Hongfei Ye and Bin Chen and Wenxi Liu and Yu Zhang and Zhao Li and Dandan Ni and Hongyang Chen},
journal= {arXiv preprint arXiv:2507.11153},
year = {2025}
}