Implicit vs. Explicit Prompting Strategies for LVLMs in Referential Communication
On the map: Multimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
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.
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.
Builds on
7 of 53 references.
References · 7
- 2024Auxiliary task demands mask the capabilities of smaller language modelscited by 54
- 2019Characterizing the dynamics of learning in repeated reference gamescited by 34
- 2024Talk Less, Interact Better: Evaluating In-context Conversational Adaptation in Multimodal LLMscited by 18
- 2025LVLMs are Bad at Overhearing Human Referential Communicationcited by 8
- 2026LVLMs and Humans Ground Differently in Referential Communicationcited by 8
- 2025Post-training for Efficient Communication via Convention Formationcited by 7
- 2026LLMs and people both learn to form conventions -- just not with each othercited by 5
Built on by
Not cited yet.
Similar, not cited
Close in wording, no citation either way
- 2025Vision-Language Models Are Not Pragmatically Competent in Referring Expression Generation
- 2026A Dynamic-Semantics Framework for Grounding Human Referring Expressions in Visual Perceptual Data
- 2023VRPTEST: Evaluating Visual Referring Prompting in Large Multimodal Models
- 2024R2-Bench: Benchmarking the Robustness of Referring Perception Models under Perturbations
- 2026AtelierEval: Agentic Evaluation of Humans & LLMs as Text-to-Image Prompters
- 2024A Systematic Survey of Prompt Engineering in Large Language Models: Techniques and Applications
- 2025The Future of MLLM Prompting is Adaptive: A Comprehensive Experimental Evaluation of Prompt Engineering Methods for Robust Multimodal Performance
- 2026RoboIRGBench: Benchmarking Implicit Referential Grounding in Vision-Language-Action Models