Abstract
Two recent studies (Jones et al. (2026); Zeng et al. (2026)) reach apparently contradictory conclusions about whether LVLMs can coordinate 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 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 implicit prompt, highlighting critical differences between how humans and AI systems communicate.
Blogger's Review: This article provides valuable insights into the performance of LVLMs under different prompting strategies, emphasizing the significance of explicit prompts in enhancing communicative efficiency. This serves as an important reference for future AI system designs, especially in complex communication tasks. Understanding the communication differences between humans and AI will be key to achieving more natural interactions.