# Rethinking Aleatoric and Epistemic Uncertainty

arXiv: https://arxiv.org/abs/2412.20892 · HTML: https://mlsanity.com/paper/2412.20892/

## Key facts

- Cited by 42 papers in the map (data through 14 Oct 2026).
- Builds on 38 of its 87 references that are in the map.
- First posted on arXiv 30 Dec 2024.

## Builds on (most cited first, 30 of 38)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision?](https://mlsanity.com/paper/1703.04977/) (2017)
- [Aleatoric and Epistemic Uncertainty in Machine Learning: An Introduction to Concepts and Methods](https://mlsanity.com/paper/1910.09457/) (2019)
- [Deep Bayesian Active Learning with Image Data](https://mlsanity.com/paper/1703.02910/) (2017)
- [BatchBALD: Efficient and Diverse Batch Acquisition for Deep Bayesian Active Learning](https://mlsanity.com/paper/1906.08158/) (2019)
- [Aleatoric uncertainty estimation with test-time augmentation for medical image segmentation with convolutional neural networks](https://mlsanity.com/paper/1807.07356/) (2018)
- [Deep Deterministic Uncertainty: A Simple Baseline](https://mlsanity.com/paper/2102.11582/) (2021)
- [Understanding Measures of Uncertainty for Adversarial Example Detection](https://mlsanity.com/paper/1803.08533/) (2018)
- [Quantifying Aleatoric and Epistemic Uncertainty in Machine Learning: Are Conditional Entropy and Mutual Information Appropriate Measures?](https://mlsanity.com/paper/2209.03302/) (2022)
- [Epistemic Neural Networks](https://mlsanity.com/paper/2107.08924/) (2021)
- [Scalable Marginal Likelihood Estimation for Model Selection in Deep Learning](https://mlsanity.com/paper/2104.04975/) (2021)
- [DEUP: Direct Epistemic Uncertainty Prediction](https://mlsanity.com/paper/2102.08501/) (2021)
- [A Deeper Look into Aleatoric and Epistemic Uncertainty Disentanglement](https://mlsanity.com/paper/2204.09308/) (2022)
- [Benchmarking Uncertainty Disentanglement: Specialized Uncertainties for Specialized Tasks](https://mlsanity.com/paper/2402.19460/) (2024)
- [Prediction-Oriented Bayesian Active Learning](https://mlsanity.com/paper/2304.08151/) (2023)
- [Evaluating Superhuman Models with Consistency Checks](https://mlsanity.com/paper/2306.09983/) (2023)
- [On Uncertainty, Tempering, and Data Augmentation in Bayesian Classification](https://mlsanity.com/paper/2203.16481/) (2022)
- [Martingale posterior distributions](https://mlsanity.com/paper/2103.15671/) (2021)
- [Exploiting Epistemic Uncertainty of Anatomy Segmentation for Anomaly Detection in Retinal OCT](https://mlsanity.com/paper/1905.12806/) (2019)
- [Is the Volume of a Credal Set a Good Measure for Epistemic Uncertainty?](https://mlsanity.com/paper/2306.09586/) (2023)
- [On the marginal likelihood and cross-validation](https://mlsanity.com/paper/1905.08737/) (2019)
- [Stochastic Batch Acquisition: A Simple Baseline for Deep Active Learning](https://mlsanity.com/paper/2106.12059/) (2021)
- [Nonparametric Uncertainty Quantification for Single Deterministic Neural Network](https://mlsanity.com/paper/2202.03101/) (2022)
- [Second-Order Uncertainty Quantification: A Distance-Based Approach](https://mlsanity.com/paper/2312.00995/) (2023)
- [From Predictions to Decisions: The Importance of Joint Predictive Distributions](https://mlsanity.com/paper/2107.09224/) (2021)
- [Quantification of Uncertainty with Adversarial Models](https://mlsanity.com/paper/2307.03217/) (2023)
- [Introducing an Improved Information-Theoretic Measure of Predictive Uncertainty](https://mlsanity.com/paper/2311.08309/) (2023)
- [From Risk to Uncertainty: Generating Predictive Uncertainty Measures via Bayesian Estimation](https://mlsanity.com/paper/2402.10727/) (2024)
- [Label-wise Aleatoric and Epistemic Uncertainty Quantification](https://mlsanity.com/paper/2406.02354/) (2024)
- [Quantifying Aleatoric and Epistemic Uncertainty with Proper Scoring Rules](https://mlsanity.com/paper/2404.12215/) (2024)

## Built on by (most cited first, 30 of 42)

- [BED-LLM: Intelligent Information Gathering with LLMs and Bayesian Experimental Design](https://mlsanity.com/paper/2508.21184/) (2025)
- [Generative Uncertainty in Diffusion Models](https://mlsanity.com/paper/2502.20946/) (2025)
- [The Illusion of Certainty: Uncertainty Quantification for LLMs Fails under Ambiguity](https://mlsanity.com/paper/2511.04418/) (2025)
- [Integral Imprecise Probability Metrics](https://mlsanity.com/paper/2505.16156/) (2025)
- [Position: Epistemic uncertainty estimation methods are fundamentally incomplete](https://mlsanity.com/paper/2505.23506/) (2025)
- [Flow Stochastic Segmentation Networks](https://mlsanity.com/paper/2507.18838/) (2025)
- [HybridFlow: Quantification of Aleatoric and Epistemic Uncertainty with a Single Hybrid Model](https://mlsanity.com/paper/2510.05054/) (2025)
- [A Geometric Approach to Optimal Experimental Design](https://mlsanity.com/paper/2510.14848/) (2025)
- [Task-Awareness Improves LLM Generations and Uncertainty](https://mlsanity.com/paper/2601.21500/) (2026)
- [WIMLE: Uncertainty-Aware World Models with IMLE for Sample-Efficient Continuous Control](https://mlsanity.com/paper/2602.14351/) (2026)
- [Uncertainty in Physics and AI: Taxonomy, Quantification, and Validation](https://mlsanity.com/paper/2605.10378/) (2026)
- [Uncertainty Decomposition for Clarification Seeking in LLM Agents](https://mlsanity.com/paper/2606.19559/) (2026)
- [Deep Ensembles for Epistemic Uncertainty: A Frequentist Perspective](https://mlsanity.com/paper/2510.22063/) (2025)
- [Beyond Accuracy: An Empirical Study of Uncertainty Estimation in Imputation](https://mlsanity.com/paper/2511.21607/) (2025)
- [Unreliable Uncertainty Estimates with Monte Carlo Dropout](https://mlsanity.com/paper/2512.14851/) (2025)
- [Loss-Driven Bayesian Active Learning](https://mlsanity.com/paper/2604.11995/) (2026)
- [Efficient Adaptive Data Acquisition via Pretrained Belief Representations](https://mlsanity.com/paper/2606.25197/) (2026)
- [Credal Large Language Models for Semantic Commitment under Uncertainty](https://mlsanity.com/paper/2608.23244/) (2026)
- [Trust Me, I Know the Way: Predictive Uncertainty in the Presence of Shortcut Learning](https://mlsanity.com/paper/2502.09137/) (2025)
- [Uncertainty Quantification with Proper Scoring Rules: Adjusting Measures to Prediction Tasks](https://mlsanity.com/paper/2505.22538/) (2025)
- [Automated C-Arm Positioning via Conformal Landmark Localization](https://mlsanity.com/paper/2510.16160/) (2025)
- [Subjective Risk Decomposition: A New View for Uncertainty Quantification](https://mlsanity.com/paper/2607.15196/) (2026)
- [Localising Dropout Variance in Twin Networks](https://mlsanity.com/paper/2507.03622/) (2025)
- [The Architecture of Trust: A Framework for AI-Augmented Real Estate Valuation in the Era of Structured Data](https://mlsanity.com/paper/2508.02765/) (2025)
- [Prediction-Oriented Subsampling from Data Streams](https://mlsanity.com/paper/2508.03868/) (2025)
- [Self-Supervised Uncertainty Estimation For Super-Resolution of Satellite Images](https://mlsanity.com/paper/2603.14074/) (2026)
- [Informative Perturbation Selection for Uncertainty-Aware Post-hoc Explanations](https://mlsanity.com/paper/2603.14894/) (2026)
- [Trustworthy deep domain adaptation for wearable photoplethysmography signal analysis with decision-theoretic uncertainty quantification](https://mlsanity.com/paper/2604.17480/) (2026)
- [The Limits of AI-Driven Allocation: Optimal Screening under Aleatoric Uncertainty](https://mlsanity.com/paper/2605.07979/) (2026)
- [U-SEG: Uncertainty in SEGmentation -- A systematic multi-variable exploration](https://mlsanity.com/paper/2605.15421/) (2026)

## Abstract (arXiv)

The ideas of aleatoric and epistemic uncertainty are widely used to reason about the probabilistic predictions of machine-learning models. We identify incoherence in existing discussions of these ideas and suggest this stems from the aleatoric-epistemic view being insufficiently expressive to capture all the distinct quantities that researchers are interested in. To address this we present a decision-theoretic perspective that relates rigorous notions of uncertainty, predictive performance and statistical dispersion in data. This serves to support clearer thinking as the field moves forward. Additionally we provide insights into popular information-theoretic quantities, showing they can be poor estimators of what they are often purported to measure, while also explaining how they can still be useful in guiding data acquisition.