# The Anatomy of Uncertainty in LLMs

arXiv: https://arxiv.org/abs/2603.24967 · HTML: https://mlsanity.com/paper/2603.24967/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 12 of its 28 references that are in the map.
- First posted on arXiv 26 Mar 2026.

## Builds on (most cited first, 12 of 12)

- [TriviaQA: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehension](https://mlsanity.com/paper/1705.03551/) (2017)
- [Language Models (Mostly) Know What They Know](https://mlsanity.com/paper/2207.05221/) (2022)
- [Decomposing Uncertainty for Large Language Models through Input Clarification Ensembling](https://mlsanity.com/paper/2311.08718/) (2023)
- [QuestBench: Can LLMs ask the right question to acquire information in reasoning tasks?](https://mlsanity.com/paper/2503.22674/) (2025)
- [A Survey of Uncertainty Estimation in LLMs: Theory Meets Practice](https://mlsanity.com/paper/2410.15326/) (2024)
- [Optimising Calls to Large Language Models with Uncertainty-Based Two-Tier Selection](https://mlsanity.com/paper/2405.02134/) (2024)
- [What Prompts Don't Say: Understanding and Managing Underspecification in LLM Prompts](https://mlsanity.com/paper/2505.13360/) (2025)
- [Disentangling Epistemic and Aleatoric Uncertainty in Reinforcement Learning](https://mlsanity.com/paper/2206.01558/) (2022)
- [An Empirical Analysis of Uncertainty in Large Language Model Evaluations](https://mlsanity.com/paper/2502.10709/) (2025)
- [The Role of Predictive Uncertainty and Diversity in Embodied AI and Robot Learning](https://mlsanity.com/paper/2405.03164/) (2024)
- [Self-Routing RAG: Binding Selective Retrieval with Knowledge Verbalization](https://mlsanity.com/paper/2504.01018/) (2025)
- [SUGAR: Leveraging Contextual Confidence for Smarter Retrieval](https://mlsanity.com/paper/2501.04899/) (2025)

## Built on by (most cited first, 2 of 2)

- [A Systematic Evaluation of Black-Box Uncertainty Estimation Methods for Large Language Models](https://mlsanity.com/paper/2606.19868/) (2026)
- [LODESTAR: Robust Entropy-Based Answer Selection in Retrieval-Augmented Generation for Question Answering -- Directing Frozen-LLM Entropy with a Reinforcement-Learned Prompt Polarizer under Misleading Passages](https://mlsanity.com/paper/2608.11922/) (2026)

## Abstract (arXiv)

Understanding why a large language model (LLM) is uncertain about the response is important for their reliable deployment. Current approaches, which either provide a single uncertainty score or rely on the classical aleatoric-epistemic dichotomy, fail to offer actionable insights for improving the generative model. Recent studies have also shown that such methods are not enough for understanding uncertainty in LLMs. In this work, we advocate for an uncertainty decomposition framework that dissects LLM uncertainty into three distinct semantic components: (i) input ambiguity, arising from ambiguous prompts; (ii) knowledge gaps, caused by insufficient parametric evidence; and (iii) decoding randomness, stemming from stochastic sampling. Through a series of experiments we demonstrate that the dominance of these components can shift across model size and task. Our framework provides a better understanding to audit LLM reliability and detect hallucinations, paving the way for targeted interventions and more trustworthy systems.