# Calibrated Ambiguity in Multimodal Language Models: Humans reach for cultural references, while models describe the picture

arXiv: https://arxiv.org/abs/2609.12575 · HTML: https://mlsanity.com/paper/2609.12575/

## 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 12 of its 83 references that are in the map.
- First posted on arXiv 11 Sep 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, 12 of 12)

- [A Roadmap to Pluralistic Alignment](https://mlsanity.com/paper/2402.05070/) (2024)
- [A theory of appropriateness with applications to generative artificial intelligence](https://mlsanity.com/paper/2412.19010/) (2024)
- [Provocations from the Humanities for Generative AI Research](https://mlsanity.com/paper/2502.19190/) (2025)
- [Meaning Is Not A Metric: Using LLMs to make cultural context legible at scale](https://mlsanity.com/paper/2505.23785/) (2025)
- [Task-Dependent Evaluation of LLM Output Homogenization: A Taxonomy-Guided Framework](https://mlsanity.com/paper/2509.21267/) (2025)
- [VAGUE: Visual Contexts Clarify Ambiguous Expressions](https://mlsanity.com/paper/2411.14137/) (2024)
- [Creative Captioning: An AI Grand Challenge Based on the Dixit Board Game](https://mlsanity.com/paper/2010.00048/) (2020)
- [Evaluation of Cultural Competence of Vision-Language Models](https://mlsanity.com/paper/2505.22793/) (2025)
- [Ambiguity Collapse by LLMs: A Taxonomy of Epistemic Risks](https://mlsanity.com/paper/2603.05801/) (2026)
- [AI as Entertainment](https://mlsanity.com/paper/2601.08768/) (2026)
- [AI as a Tool for Simulation-Based Experiments in Literary Studies](https://mlsanity.com/paper/2606.02293/) (2026)
- [AI Fiction in the Wild](https://mlsanity.com/paper/2606.22748/) (2026)

## Abstract (arXiv)

Ambiguity is often treated as a bug for AI systems to resolve---but in human communication and culture, ambiguity can also be a generative resource. From humour to politics to art, people express themselves in words and images that are open enough to invite different interpretations, yet constrained enough to be interpretable. We operationalise this notion of calibrated ambiguity with a task drawn from the parlour game Dixit. We compare differences in clues generated by human vs multimodal language models, based on a novel coding rubric for calibrated ambiguity, and find that models consistently exhibit ambiguity collapse (i.e., their outputs are over-specified, leaving no room for multiple legitimate interpretations). Unlike human clues, AI-generated clues also exhibit cultural flattening; they almost never make reference to culturally-situated knowledge, even when prompted to use allusion and figurative language.