Implicit vs. Explicit Prompting Strategies for LVLMs in Referential Communication
Quick summary
arXiv:2606.17372v3 Announce Type: replace-cross 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, w
Key takeaways
- arXiv:2606.17372v3 Announce Type: replace-cross 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.
Why it matters
The importance of “Implicit vs. Explicit Prompting Strategies for LVLMs in Referential Communication” will be measured by what changes in practice. User behavior, access conditions, verifiable performance and responsible-use outcomes are the signals worth following.
Member comments