Lexical Availability and Human Distributional Agreement in GPT-4o’s Color Naming

Anna Feldman, Jing Peng


Abstract
We evaluate GPT-4o’s color naming across nine languages using both synthetic and human-derived stimuli. Using hue wheels, fixed basic categories, low-chroma hue lines, and dense binned CIELAB grids, we separate lexical availability of color terms from distributional agreement with human color naming. GPT-4o reliably names vivid, high-chroma colors and reproduces several known language-specific distinctions under constrained settings. However, its performance degrades sharply for low-chroma colors and for stimuli near human category boundaries. In these regions, model-human divergence remains high. Overall, GPT-4o shows strong cross-linguistic lexical knowledge but does not reliably match human color-naming distributions, especially in low-chroma and boundary regions.
Anthology ID:
2026.starsem-conference.9
Volume:
Proceedings of the 15th Joint Conference on Lexical and Computational Semantics (*SEM 2026)
Month:
July
Year:
2026
Address:
San Diego, California, United States
Editors:
Saif M. Mohammad, Nedjma Ousidhoum
Venues:
*SEM | WS
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
136–147
Language:
URL:
https://preview.aclanthology.org/ingest-acl-workshops/2026.starsem-conference.9/
DOI:
Bibkey:
Cite (ACL):
Anna Feldman and Jing Peng. 2026. Lexical Availability and Human Distributional Agreement in GPT-4o’s Color Naming. In Proceedings of the 15th Joint Conference on Lexical and Computational Semantics (*SEM 2026), pages 136–147, San Diego, California, United States. Association for Computational Linguistics.
Cite (Informal):
Lexical Availability and Human Distributional Agreement in GPT-4o’s Color Naming (Feldman & Peng, *SEM 2026)
Copy Citation:
PDF:
https://preview.aclanthology.org/ingest-acl-workshops/2026.starsem-conference.9.pdf