mlsanityData to 7 Oct 2026

Rethinking Aleatoric and Epistemic Uncertainty

arXiv 2412.20892 ↗First posted 30 Dec 2024cs.LG stat.MLcited by 40

Not on the map. Why?

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.

Key facts. Cited by 40 papers in the map (data through 7 Oct 2026). Builds on 38 of its 87 references that are in the map. First posted on arXiv 30 Dec 2024.

Builds on

38 of 87 references.

References · 38

  1. 2020Language Models are Few-Shot Learnerscited by 32,199
  2. 2017What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision?cited by 2,335
  3. 2019Aleatoric and Epistemic Uncertainty in Machine Learning: An Introduction to Concepts and Methodscited by 903
  4. 2017Deep Bayesian Active Learning with Image Datacited by 812
  5. 2019BatchBALD: Efficient and Diverse Batch Acquisition for Deep Bayesian Active Learningcited by 428
  6. 2018Aleatoric uncertainty estimation with test-time augmentation for medical image segmentation with convolutional neural networkscited by 278
  7. 2021Deep Deterministic Uncertainty: A Simple Baselinecited by 200
  8. 2018Understanding Measures of Uncertainty for Adversarial Example Detectioncited by 177
  9. 2022Quantifying Aleatoric and Epistemic Uncertainty in Machine Learning: Are Conditional Entropy and Mutual Information Appropriate Measures?cited by 124
  10. 2021Epistemic Neural Networkscited by 120
  11. 2021Scalable Marginal Likelihood Estimation for Model Selection in Deep Learningcited by 105
  12. 2021DEUP: Direct Epistemic Uncertainty Predictioncited by 102
26 more
  1. 2022A Deeper Look into Aleatoric and Epistemic Uncertainty Disentanglementcited by 87
  2. 2024Benchmarking Uncertainty Disentanglement: Specialized Uncertainties for Specialized Taskscited by 78
  3. 2023Prediction-Oriented Bayesian Active Learningcited by 60
  4. 2023Evaluating Superhuman Models with Consistency Checkscited by 47
  5. 2022On Uncertainty, Tempering, and Data Augmentation in Bayesian Classificationcited by 46
  6. 2021Martingale posterior distributionscited by 43
  7. 2019Exploiting Epistemic Uncertainty of Anatomy Segmentation for Anomaly Detection in Retinal OCTcited by 41
  8. 2023Is the Volume of a Credal Set a Good Measure for Epistemic Uncertainty?cited by 40
  9. 2019On the marginal likelihood and cross-validationcited by 36
  10. 2021Stochastic Batch Acquisition: A Simple Baseline for Deep Active Learningcited by 36
  11. 2022Nonparametric Uncertainty Quantification for Single Deterministic Neural Networkcited by 36
  12. 2023Second-Order Uncertainty Quantification: A Distance-Based Approachcited by 35
  13. 2021From Predictions to Decisions: The Importance of Joint Predictive Distributionscited by 28
  14. 2023Quantification of Uncertainty with Adversarial Modelscited by 28
  15. 2023Introducing an Improved Information-Theoretic Measure of Predictive Uncertaintycited by 28
  16. 2024From Risk to Uncertainty: Generating Predictive Uncertainty Measures via Bayesian Estimationcited by 27
  17. 2024Label-wise Aleatoric and Epistemic Uncertainty Quantificationcited by 22
  18. 2024Quantifying Aleatoric and Epistemic Uncertainty with Proper Scoring Rulescited by 21
  19. 2024Amortized Bayesian Experimental Design for Decision-Makingcited by 20
  20. 2023Second-Order Uncertainty Quantification: Variance-Based Measurescited by 19
  21. 2021Bayesian OOD detection with aleatoric uncertainty and outlier exposurecited by 16
  22. 2024On Information-Theoretic Measures of Predictive Uncertaintycited by 16
  23. 2020The Hidden Uncertainty in a Neural Networks Activationscited by 14
  24. 2022Generalizing Bayesian Optimization with Decision-theoretic Entropiescited by 11
  25. 2024Making Better Use of Unlabelled Data in Bayesian Active Learningcited by 10
  26. 2019U2-Net: A Bayesian U-Net model with epistemic uncertainty feedback for photoreceptor layer segmentation in pathological OCT scanscited by 9

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 17; 2026: 23.

40 papers.

Sort:

By area:

  1. 2025BED-LLM: Intelligent Information Gathering with LLMs and Bayesian Experimental Designcited by 21
  2. 2025Generative Uncertainty in Diffusion Modelscited by 20
  3. 2025The Illusion of Certainty: Uncertainty Quantification for LLMs Fails under Ambiguitycited by 15
  4. 2025Integral Imprecise Probability Metricscited by 11
  5. 2025Position: Epistemic uncertainty estimation methods are fundamentally incompletecited by 8
  6. 2025Flow Stochastic Segmentation Networkscited by 3
  7. 2025HybridFlow: Quantification of Aleatoric and Epistemic Uncertainty with a Single Hybrid Modelcited by 3
  8. 2026WIMLE: Uncertainty-Aware World Models with IMLE for Sample-Efficient Continuous Controlcited by 3
  9. 2026Uncertainty in Physics and AI: Taxonomy, Quantification, and Validationcited by 3
  10. 2026Uncertainty Decomposition for Clarification Seeking in LLM Agentscited by 3
  11. 2025A Geometric Approach to Optimal Experimental Designcited by 2
  12. 2025Beyond Accuracy: An Empirical Study of Uncertainty Estimation in Imputationcited by 2
28 more
  1. 2025Unreliable Uncertainty Estimates with Monte Carlo Dropoutcited by 2
  2. 2026Task-Awareness Improves LLM Generations and Uncertaintycited by 2
  3. 2026Efficient Adaptive Data Acquisition via Pretrained Belief Representationscited by 2
  4. 2026Credal Large Language Models for Semantic Commitment under Uncertaintycited by 2
  5. 2025Trust Me, I Know the Way: Predictive Uncertainty in the Presence of Shortcut Learningcited by 1
  6. 2025Uncertainty Quantification with Proper Scoring Rules: Adjusting Measures to Prediction Taskscited by 1
  7. 2025Automated C-Arm Positioning via Conformal Landmark Localizationcited by 1
  8. 2025Deep Ensembles for Epistemic Uncertainty: A Frequentist Perspectivecited by 1
  9. 2026Loss-Driven Bayesian Active Learningcited by 1
  10. 2026Subjective Risk Decomposition: A New View for Uncertainty Quantificationcited by 1
  11. 2025Localising Dropout Variance in Twin Networkscited by 0
  12. 2025The Architecture of Trust: A Framework for AI-Augmented Real Estate Valuation in the Era of Structured Datacited by 0
  13. 2025Prediction-Oriented Subsampling from Data Streamscited by 0
  14. 2026Self-Supervised Uncertainty Estimation For Super-Resolution of Satellite Imagescited by 0
  15. 2026Informative Perturbation Selection for Uncertainty-Aware Post-hoc Explanationscited by 0
  16. 2026Trustworthy deep domain adaptation for wearable photoplethysmography signal analysis with decision-theoretic uncertainty quantificationcited by 0
  17. 2026The Limits of AI-Driven Allocation: Optimal Screening under Aleatoric Uncertaintycited by 0
  18. 2026U-SEG: Uncertainty in SEGmentation -- A systematic multi-variable explorationcited by 0
  19. 2026iSAGE: A Human-in-the-Loop Framework for Remote Sensing Semantic Segmentation via Sparse Point Supervisioncited by 0
  20. 2026Can we trust our models? Epistemic calibration in second-order classificationcited by 0
  21. 2026Quantifying Aleatoric Uncertainty of In-Context Learning for Robust Measure of LLM Prediction Confidencecited by 0
  22. 2026Controllable Diversity in Normalization-Based Implicit Ensembles via Softmax-Temperature Modulationcited by 0
  23. 2026Why Does the Future Branch? Identifiable Closure Tests for Stochastic Physical World Modelscited by 0
  24. 2026Improved Confidence Estimates for Black-Box Large Language Modelscited by 0
  25. 2026Flexible Spectral-Normalized Neural Gaussian Process for Dynamic Aperture Predictioncited by 0
  26. 2026Optimal Transport Dropout for Structured Predictive Uncertaintycited by 0
  27. 2026XU-RS: Explaining Credal Width in Random-Set Language Modelscited by 0
  28. 2026Beyond Answer Confidence: A Controlled Audit of Self-Knowledge in a Black-Box Decision Modelcited by 0