Implicit vs. Explicit Prompting Strategies for LVLMs in Referential Communication

Title:Implicit vs. Explicit Prompting Strategies for LVLMs in Referential Communication

Abstract:Two recent studies \citep{jones2026llms, zeng2026lvlms} reach apparently contradictory conclusions about whether large vision-language models (LVLMs) can coordinate similarly to humans on efficient referring expressions. We control for task differences between the studies while directly comparing their prompting styles. We replicate the finding that models can coordinate efficient referring expressions when \textit{explicitly} prompted to do so, suggesting that other task differences are not responsible for divergent results. However, we also find that the same models fail to infer the need for communicative efficiency from a more \textit{implicit} prompt, highlighting critical differences between how humans and AI systems communicate.

Computation and Language (cs.CL); Artificial Intelligence (cs.AI)

arXiv:2606.17372 [cs.CL]

(or arXiv:2606.17372v3 [cs.CL] for this version)

https://doi.org/10.48550/arXiv.2606.17372 Focus to learn more arXiv-issued DOI via DataCite

arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.

Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.

Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.