# Implicit vs. Explicit Prompting Strategies for LVLMs in Referential Communication

arXiv: https://arxiv.org/abs/2606.17372 · HTML: https://mlsanity.com/paper/2606.17372/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in VLM benchmarks and visual reasoning, one of 16 directions in Multimodal LLMs / vision-language models.
- Builds on 7 of its 53 references that are in the map.
- First posted on arXiv 16 Jun 2026.

## Placed in

- Multimodal LLMs / vision-language models / [VLM benchmarks and visual reasoning](https://mlsanity.com/mllm/vlm-benchmarks-and-visual-reasoning/)

## Builds on (most cited first, 7 of 7)

- [Auxiliary task demands mask the capabilities of smaller language models](https://mlsanity.com/paper/2404.02418/) (2024)
- [Characterizing the dynamics of learning in repeated reference games](https://mlsanity.com/paper/1912.07199/) (2019)
- [Talk Less, Interact Better: Evaluating In-context Conversational Adaptation in Multimodal LLMs](https://mlsanity.com/paper/2408.01417/) (2024)
- [LVLMs are Bad at Overhearing Human Referential Communication](https://mlsanity.com/paper/2509.11514/) (2025)
- [LVLMs and Humans Ground Differently in Referential Communication](https://mlsanity.com/paper/2601.19792/) (2026)
- [Post-training for Efficient Communication via Convention Formation](https://mlsanity.com/paper/2508.06482/) (2025)
- [LLMs and people both learn to form conventions -- just not with each other](https://mlsanity.com/paper/2602.08208/) (2026)

## Abstract (arXiv)

Two recent studies citepjones2026llms, 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 textitexplicitly 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 textitimplicit prompt, highlighting critical differences between how humans and AI systems communicate.