# Ambiguity Collapse by LLMs: A Taxonomy of Epistemic Risks

arXiv: https://arxiv.org/abs/2603.05801 · HTML: https://mlsanity.com/paper/2603.05801/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 58 of its 176 references that are in the map.
- First posted on arXiv 6 Mar 2026.

## Builds on (most cited first, 30 of 58)

- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena](https://mlsanity.com/paper/2306.05685/) (2023)
- [A Survey on LLM-as-a-Judge](https://mlsanity.com/paper/2411.15594/) (2024)
- [Language (Technology) is Power: A Critical Survey of "Bias" in NLP](https://mlsanity.com/paper/2005.14050/) (2020)
- [Whose Opinions Do Language Models Reflect?](https://mlsanity.com/paper/2303.17548/) (2023)
- [The Mythos of Model Interpretability](https://mlsanity.com/paper/1606.03490/) (2016)
- [Underspecification Presents Challenges for Credibility in Modern Machine Learning](https://mlsanity.com/paper/2011.03395/) (2020)
- [LLMs-as-Judges: A Comprehensive Survey on LLM-based Evaluation Methods](https://mlsanity.com/paper/2412.05579/) (2024)
- [AmbigQA: Answering Ambiguous Open-domain Questions](https://mlsanity.com/paper/2004.10645/) (2020)
- [Dealing with Disagreements: Looking Beyond the Majority Vote in Subjective Annotations](https://mlsanity.com/paper/2110.05719/) (2021)
- [Easily Accessible Text-to-Image Generation Amplifies Demographic Stereotypes at Large Scale](https://mlsanity.com/paper/2211.03759/) (2022)
- [The Capacity for Moral Self-Correction in Large Language Models](https://mlsanity.com/paper/2302.07459/) (2023)
- [Political Compass or Spinning Arrow? Towards More Meaningful Evaluations for Values and Opinions in Large Language Models](https://mlsanity.com/paper/2402.16786/) (2024)
- [Cultural Bias and Cultural Alignment of Large Language Models](https://mlsanity.com/paper/2311.14096/) (2023)
- [Co-Writing with Opinionated Language Models Affects Users' Views](https://mlsanity.com/paper/2302.00560/) (2023)
- [Investigating Cultural Alignment of Large Language Models](https://mlsanity.com/paper/2402.13231/) (2024)
- [Collective Constitutional AI: Aligning a Language Model with Public Input](https://mlsanity.com/paper/2406.07814/) (2024)
- [Modular Pluralism: Pluralistic Alignment via Multi-LLM Collaboration](https://mlsanity.com/paper/2406.15951/) (2024)
- [Taming Overconfidence in LLMs: Reward Calibration in RLHF](https://mlsanity.com/paper/2410.09724/) (2024)
- [Your Brain on ChatGPT: Accumulation of Cognitive Debt when Using an AI Assistant for Essay Writing Task](https://mlsanity.com/paper/2506.08872/) (2025)
- [Picking on the Same Person: Does Algorithmic Monoculture lead to Outcome Homogenization?](https://mlsanity.com/paper/2211.13972/) (2022)
- [LLM-in-the-loop: Leveraging Large Language Model for Thematic Analysis](https://mlsanity.com/paper/2310.15100/) (2023)
- [Is Your Toxicity My Toxicity? Exploring the Impact of Rater Identity on Toxicity Annotation](https://mlsanity.com/paper/2205.00501/) (2022)
- [Beware of Metacognitive Laziness: Effects of Generative Artificial Intelligence on Learning Motivation, Processes, and Performance](https://mlsanity.com/paper/2412.09315/) (2024)
- [Aligning Language Models to Explicitly Handle Ambiguity](https://mlsanity.com/paper/2404.11972/) (2024)
- [CLAMBER: A Benchmark of Identifying and Clarifying Ambiguous Information Needs in Large Language Models](https://mlsanity.com/paper/2405.12063/) (2024)
- [Randomness, Not Representation: The Unreliability of Evaluating Cultural Alignment in LLMs](https://mlsanity.com/paper/2503.08688/) (2025)
- [Position: Model Collapse Does Not Mean What You Think](https://mlsanity.com/paper/2503.03150/) (2025)
- [What Prompts Don't Say: Understanding and Managing Underspecification in LLM Prompts](https://mlsanity.com/paper/2505.13360/) (2025)
- [Asking Clarification Questions to Handle Ambiguity in Open-Domain QA](https://mlsanity.com/paper/2305.13808/) (2023)

## Built on by (most cited first, 3 of 3)

- [Calibrated Ambiguity in Multimodal Language Models: Humans reach for cultural references, while models describe the picture](https://mlsanity.com/paper/2609.12575/) (2026)
- [LLMs as Oracles: Reliance on LLMs for Subjective Personal Questions](https://mlsanity.com/paper/2609.14849/) (2026)
- [Narrowing the Horizon: Quantifying Topic Saliency Shifts in Generative Monoculture](https://mlsanity.com/paper/2609.35302/) (2026)

## Abstract (arXiv)

Large language models (LLMs) are increasingly used to make sense of ambiguous, open-textured, value-laden terms. Platforms routinely rely on LLMs for content moderation, asking them to label text based on disputed concepts like "hate speech" or "incitement"; hiring managers may use LLMs to rank who counts as "qualified"; and AI labs increasingly train models to self-regulate under constitutional-style ambiguous principles such as "biased" or "legitimate". This paper introduces ambiguity collapse: a phenomenon that occurs when an LLM encounters a term that genuinely admits multiple legitimate interpretations, yet produces a singular resolution, in ways that bypass the human practices through which meaning is ordinarily negotiated, contested, and justified. Drawing on interdisciplinary accounts of ambiguity as a productive epistemic resource, we develop a taxonomy of the epistemic risks posed by ambiguity collapse at three levels: process (foreclosing opportunities to deliberate, develop cognitive skills, and shape contested terms), output (distorting the concepts and reasons agents act upon), and ecosystem (reshaping shared vocabularies, interpretive norms, and how concepts evolve over time). We illustrate these risks through three case studies, and conclude by sketching multi-layer mitigation principles spanning training, institutional deployment design, interface affordances, and the management of underspecified prompts, with the goal of designing systems that surface, preserve, and responsibly govern ambiguity.