mlsanityData to 7 Oct 2026

Aleatoric and Epistemic Uncertainty in Machine Learning: An Introduction to Concepts and Methods

arXiv 1910.09457 ↗First posted 21 Oct 2019cs.LG stat.MLcited by 903

Not on the map. Why?

Cited by 22 in Diffusion models, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

The notion of uncertainty is of major importance in machine learning and constitutes a key element of machine learning methodology. In line with the statistical tradition, uncertainty has long been perceived as almost synonymous with standard probability and probabilistic predictions. Yet, due to the steadily increasing relevance of machine learning for practical applications and related issues such as safety requirements, new problems and challenges have recently been identified by machine learning scholars, and these problems may call for new methodological developments. In particular, this includes the importance of distinguishing between (at least) two different types of uncertainty, often referred to as aleatoric and epistemic. In this paper, we provide an introduction to the topic of uncertainty in machine learning as well as an overview of attempts so far at handling uncertainty in general and formalizing this distinction in particular.

Key facts. Cited by 903 papers in the map (data through 7 Oct 2026). First posted on arXiv 21 Oct 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 64; 2022: 121; 2023: 138; 2024: 192; 2025: 207; 2026: 181.

903 papers.

Sort:

By area:

  1. 2021A Survey of Uncertainty in Deep Neural Networkscited by 675
  2. 2022A Survey of Machine Unlearningcited by 298
  3. 2023Generating with Confidence: Uncertainty Quantification for Black-box Large Language Modelscited by 286
  4. 2022Uncertainty Quantification in Scientific Machine Learning: Methods, Metrics, and Comparisonscited by 169
  5. 2023A Survey on Graph Neural Networks for Time Series: Forecasting, Classification, Imputation, and Anomaly Detectioncited by 145
  6. 2024Rho-1: Not All Tokens Are What You Needcited by 132
  7. 2022Quantifying Aleatoric and Epistemic Uncertainty in Machine Learning: Are Conditional Entropy and Mutual Information Appropriate Measures?cited by 124
  8. 2023AI Transparency in the Age of LLMs: A Human-Centered Research Roadmapcited by 119
  9. 2023Decomposing Uncertainty for Large Language Models through Input Clarification Ensemblingcited by 113
  10. 2021DEUP: Direct Epistemic Uncertainty Predictioncited by 102
  11. 2025Uncertainty Quantification and Confidence Calibration in Large Language Models: A Surveycited by 93
  12. 2022A Deeper Look into Aleatoric and Epistemic Uncertainty Disentanglementcited by 87
38 more
  1. 2024On Verbalized Confidence Scores for LLMscited by 83
  2. 2021Active Learning for Deep Object Detection via Probabilistic Modelingcited by 79
  3. 2024LUQ: Long-text Uncertainty Quantification for LLMscited by 79
  4. 2023A Survey on Uncertainty Quantification Methods for Deep Learningcited by 78
  5. 2023Machine learning with data assimilation and uncertainty quantification for dynamical systems: a reviewcited by 74
  6. 2021Prior and Posterior Networks: A Survey on Evidential Deep Learning Methods For Uncertainty Estimationcited by 71
  7. 2021Classifier Calibration: A survey on how to assess and improve predicted class probabilitiescited by 71
  8. 2024Uncertainty-aware Reward Model: Teaching Reward Models to Know What is Unknowncited by 71
  9. 2022Mutual Information Alleviates Hallucinations in Abstractive Summarizationcited by 67
  10. 2022Pitfalls of Epistemic Uncertainty Quantification through Loss Minimisationcited by 65
  11. 2024A Survey on Autonomous Driving Datasets: Statistics, Annotation Quality, and a Future Outlookcited by 65
  12. 2022Deep Ensembles Work, But Are They Necessary?cited by 63
  13. 2022Training Uncertainty-Aware Classifiers with Conformalized Deep Learningcited by 62
  14. 2022Trustworthy clinical AI solutions: a unified review of uncertainty quantification in deep learning models for medical image analysiscited by 62
  15. 2023Uncertainty in Natural Language Generation: From Theory to Applicationscited by 61
  16. 2023Continual Learning: Applications and the Road Forwardcited by 59
  17. 2024Quantile Regression for Distributional Reward Models in RLHFcited by 59
  18. 2023When Does Confidence-Based Cascade Deferral Suffice?cited by 58
  19. 2025A Survey of Uncertainty Estimation Methods on Large Language Modelscited by 57
  20. 2024SPUQ: Perturbation-Based Uncertainty Quantification for Large Language Modelscited by 54
  21. 2024A Survey of Uncertainty Estimation in LLMs: Theory Meets Practicecited by 54
  22. 2023Curated LLM: Synergy of LLMs and Data Curation for tabular augmentation in low-data regimescited by 52
  23. 2024Estimating Epistemic and Aleatoric Uncertainty with a Single Modelcited by 52
  24. 2023What Comes Next? Evaluating Uncertainty in Neural Text Generators Against Human Production Variabilitycited by 51
  25. 2023C-SFDA: A Curriculum Learning Aided Self-Training Framework for Efficient Source Free Domain Adaptationcited by 49
  26. 2021Efficient Deep Reinforcement Learning with Imitative Expert Priors for Autonomous Drivingcited by 46
  27. 2022Uncertainty Quantification of Collaborative Detection for Self-Drivingcited by 46
  28. 2023Credal Bayesian Deep Learningcited by 45
  29. 2024Distinguishing the Knowable from the Unknowable with Language Modelscited by 45
  30. 2023Uncertainty in Natural Language Processing: Sources, Quantification, and Applicationscited by 44
  31. 2024Impact of Preference Noise on the Alignment Performance of Generative Language Modelscited by 41
  32. 2022The Unreasonable Effectiveness of Deep Evidential Regressioncited by 40
  33. 2023Is the Volume of a Credal Set a Good Measure for Epistemic Uncertainty?cited by 40
  34. 2023Look Before You Leap: An Exploratory Study of Uncertainty Measurement for Large Language Modelscited by 40
  35. 2024Rethinking Aleatoric and Epistemic Uncertaintycited by 40
  36. 2022Evaluating Machine Unlearning via Epistemic Uncertaintycited by 39
  37. 2023Human Uncertainty in Concept-Based AI Systemscited by 39
  38. 2023A review of uncertainty quantification in medical image analysis: probabilistic and non-probabilistic methodscited by 39

50 most cited of 903 All 903 (JSON)