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

2026-09-11

AI Summary

研究探讨了多模态语言模型在生成具有校准模糊性的线索时的问题，发现模型倾向于过度指定且缺乏文化引用，与人类生成的线索不同。

Abstract

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.

Problem

• ambiguity
• multimodal language models
• cultural references

Innovation

• Calibrated Ambiguity
• Multimodal Language Models
• Ambiguity Collapse
• Cultural Flattening