Artificial Language Learning Paradigm Reveals Pragmatic Blind Spots in Vision-Language Models

A study by Yan Cong and Julia Rayz, presented at the Third Workshop on the Bridges and Gaps between Formal and Computational Linguistics (BriGap-3) in Paris, France, in July 2026, found that current vision-language models (VLMs) capture only a restricted subset of pragmatic effects central to Gricean reasoning. Across four experiments evaluating five VLMs, the researchers found evidence of cost effects in some models, but no model consistently exhibited competition effects driven by ambiguity risk, and model scale alone did not predict pragmatic alignment; architectural choices played a larger role.

Abstract Humans are pragmatic language users who naturally and effortlessly reason about the choice of utterances that help collaborate and engage in social interactions. In this paper, we examine whether vision-language models VLMs exhibit similar pragmatic reasoning effects through a validated artificial language learning paradigm. Across four experiments, we evaluate five VLMs’ sensitivity to production cost, ambiguity-driven competition effects, and the influences of visual features and model properties. We find evidence of cost effects in some VLMs. However, no model consistently exhibits competition effects driven by ambiguity risk, a hallmark of Gricean pragmatic reasoning. We also find that model scale alone does not predict pragmatic alignment; architectural choices play a larger role. Moreover, probability-based methods reveal clearer effects than prompting. Overall, current VLMs capture only a restricted subset of pragmatic effects central to Gricean reasoning, suggesting gaps in multimodal pragmatic reasoning.- Anthology ID: - 2026.brigap-1.6 - Volume: Proceedings of the Third Workshop on the Bridges and Gaps between Formal and Computational Linguistics BriGap-3 /volumes/2026.brigap-1/ - Month: - July - Year: - 2026 - Address: - Paris, France - Editors: Timothée Bernard /people/timothee-bernard/ , Emmanuele Chersoni /people/emmanuele-chersoni/ , Giulia Rambelli /people/giulia-rambelli/unverified/ - Venues: BriGap /venues/brigap/ | WS /venues/ws/ - SIG: - Publisher: - Association for Computational Linguistics - Note: - Pages: - 50–62 - Language: - URL: https://aclanthology.org/2026.brigap-1.6/ https://aclanthology.org/2026.brigap-1.6/ - DOI: - Cite ACL : - Yan Cong and Julia Rayz. 2026. Artificial Language Learning Paradigm Reveals Pragmatic Blind Spots in Vision-Language Models https://aclanthology.org/2026.brigap-1.6/ . In Proceedings of the Third Workshop on the Bridges and Gaps between Formal and Computational Linguistics BriGap-3 , pages 50–62, Paris, France. Association for Computational Linguistics. - Cite Informal : Artificial Language Learning Paradigm Reveals Pragmatic Blind Spots in Vision-Language Models https://aclanthology.org/2026.brigap-1.6/ Cong & Rayz, BriGap 2026 - PDF: https://aclanthology.org/2026.brigap-1.6.pdf https://aclanthology.org/2026.brigap-1.6.pdf