Ambiguity Collapse by LLMs: A Taxonomy of Epistemic Risks

• URL: http://arxiv.org/abs/2603.05801v1
• Date: Fri, 06 Mar 2026 01:23:17 GMT
• Title: Ambiguity Collapse by LLMs: A Taxonomy of Epistemic Risks
• Abstract summary: Large language models (LLMs) are increasingly used to make sense of ambiguous, open-textured, value-laden terms.<n>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.
• Score: 5.45414933764086
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 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.

Related papers

• Semantic Bandits: In-Context Exploration-Exploitation is Biased by Semantic Priors [15.039508449686009]
  We study how semantically informative action labels reduce exploration in favour of exploitation.<n>We find that negative rewards trigger substantially more exploration than equivalent positive rewards.<n>We argue that the use of language to define the environment and rewards introduces unavoidable biases.
  arXiv  Detail & Related papers  (2026-08-17T15:25:18Z)
• Human-AI Co-Interpretation for Responsible AI: A Hermeneutic Perspective [4.832750949021042]
  Hermeneutic understanding is distinguished from token-prediction-based text generation.<n>Hermeneutic understanding is reserved for accountable human interpreters situated in disciplinary historical-linguistic traditions.<n>Hermeneutic understanding is distinguished from token-prediction-based text generation.
  arXiv  Detail & Related papers  (2026-08-02T18:19:13Z)
• The Periodic Table of LLM Reasoning: A Structured Survey of Reasoning Paradigms, Methods, and Failure Modes [55.42597391158023]
  This survey provides a systematic analysis of more than 300 recent papers from arXiv, Semantic Scholar, Google Scholar, Papers with Code, and the ACL Anthology.<n>We introduce a structured taxonomy of reasoning research, covering Chain-of-Thought reasoning, multi-hop reasoning, mathematical reasoning, common sense reasoning, visual and temporal reasoning, code and algorithmic reasoning, retrieval-augmented reasoning, tool-augmented and agentic reasoning, and reinforcement learning-based reasoning.<n>We synthesize recurring limitations and failure modes, such as reasoning hallucinations, brittle multi-step inference, weak causal abstraction, and poor cross
  arXiv  Detail & Related papers  (2026-06-09T21:59:37Z)
• Concept Component Analysis: A Principled Approach for Concept Extraction in LLMs [51.378834857406325]
  Mechanistic interpretability seeks to mitigate the issues through extracts from large language models.<n>Sparse autoencoders (SAEs) have emerged as a popular approach for extracting interpretable and monosemantic concepts.<n>We show that SAEs suffer from a fundamental theoretical ambiguity: the well-defined correspondence between LLM representations and human-interpretable concepts remains unclear.
  arXiv  Detail & Related papers  (2026-01-28T09:27:05Z)
• Semantic Deception: When Reasoning Models Can't Compute an Addition [0.6361348748202731]
  We investigate the so-called reasoning capabilities of large language models (LLMs) over novel symbolic representations.<n>We introduce semantic deceptions: situations in which symbols carry misleading semantic associations due to their form.<n>We show that semantic cues can significantly deteriorate reasoning models' performance on very simple tasks.
  arXiv  Detail & Related papers  (2025-12-23T22:22:18Z)
• MENTOR: A Metacognition-Driven Self-Evolution Framework for Uncovering and Mitigating Implicit Risks in LLMs on Domain Tasks [17.598413159363393]
  Current alignment efforts primarily target explicit risks such as bias, hate speech, and violence.<n>We propose MENTOR: A MEtacognition-driveN self-evoluTion framework for uncOvering and mitigating implicit risks in large language models.<n>We release a supporting dataset of 9,000 risk queries spanning education, finance, and management to enhance domain-specific risk identification.
  arXiv  Detail & Related papers  (2025-11-10T13:51:51Z)
• The Unified Cognitive Consciousness Theory for Language Models: Anchoring Semantics, Thresholds of Activation, and Emergent Reasoning [2.0800882594868293]
  Unified Cognitive Consciousness Theory (UCCT) casts them as vast unconscious pattern repositories.<n>UCCT formalizes this process as Bayesian competition between statistical priors learned in pre-training and context-driven target patterns.<n>We ground the theory in three principles: threshold crossing, modality, and density-distance predictive power.
  arXiv  Detail & Related papers  (2025-06-02T18:12:43Z)
• Are Language Models Consequentialist or Deontological Moral Reasoners? [75.6788742799773]
  We focus on a large-scale analysis of the moral reasoning traces provided by large language models (LLMs)<n>We introduce and test a taxonomy of moral rationales to systematically classify reasoning traces according to two main normative ethical theories: consequentialism and deontology.
  arXiv  Detail & Related papers  (2025-05-27T17:51:18Z)
• Language Agents Meet Causality -- Bridging LLMs and Causal World Models [50.79984529172807]
  We propose a framework that integrates causal representation learning with large language models. This framework learns a causal world model, with causal variables linked to natural language expressions. We evaluate the framework on causal inference and planning tasks across temporal scales and environmental complexities.
  arXiv  Detail & Related papers  (2024-10-25T18:36:37Z)
• RULEBREAKERS: Challenging LLMs at the Crossroads between Formal Logic and Human-like Reasoning [3.0648414540406703]
  We create RULEBREAKERS, the first dataset for rigorously evaluating the ability of large language models to recognize and respond to rulebreakers in a human-like manner.<n>We find that most models, including GPT-4o, achieve mediocre accuracy on RULEBREAKERS and exhibit some tendency to over-rigidly apply logical rules unlike what is expected from typical human reasoners.
  arXiv  Detail & Related papers  (2024-10-21T20:48:16Z)
• Phenomenal Yet Puzzling: Testing Inductive Reasoning Capabilities of Language Models with Hypothesis Refinement [92.61557711360652]
  Language models (LMs) often fall short on inductive reasoning, despite achieving impressive success on research benchmarks. We conduct a systematic study of the inductive reasoning capabilities of LMs through iterative hypothesis refinement. We reveal several discrepancies between the inductive reasoning processes of LMs and humans, shedding light on both the potentials and limitations of using LMs in inductive reasoning tasks.
  arXiv  Detail & Related papers  (2023-10-12T17:51:10Z)
• Simple Linguistic Inferences of Large Language Models (LLMs): Blind Spots and Blinds [59.71218039095155]
  We evaluate language understanding capacities on simple inference tasks that most humans find trivial. We target (i) grammatically-specified entailments, (ii) premises with evidential adverbs of uncertainty, and (iii) monotonicity entailments. The models exhibit moderate to low performance on these evaluation sets.
  arXiv  Detail & Related papers  (2023-05-24T06:41:09Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.