Epistemic Uncertainty

Ask about this topic

Overview

Epistemic uncertainty concerns what a model does not know, often distinguished from aleatoric uncertainty caused by inherent variability or ambiguity in observations. Researchers estimate it with Bayesian methods, ensembles and dropout, evidential models, and set-valued or credal predictions, then use it for out-of-distribution detection, selective prediction, active learning, and safer decisions. Work increasingly evaluates whether uncertainty is calibrated and useful for specific decisions, including through conformal guarantees, abstention tests, and benchmarks under distribution shift. A central tension is that common signals such as ensemble disagreement or predictive entropy may not reliably track missing knowledge, and their value depends on how uncertainty is defined and tested.

Latest papers

CardsList

113 papers14 papers in the last four weeks, up 250% on the four weeks before. 0.1% of all new papers.

  1. The Epistemic Support-Point Filter: Jaynesian Maximum Entropy Meets Popperian Falsification

    Mar 10, 2026Moriba Kemessia JahEpistemic UncertaintyMinimax Estimation

    Black Swan Research Group, GaiaVerse, Ltd. · Jah Decision Intelligence Group, Aerospace Engineering & Engineering Mechanics, The University of Texas at Austin

  2. Efficient Credal Prediction through Decalibration

    Mar 9, 2026Paul Hofman, Timo Löhr, Maximilian Muschalik +2Epistemic Uncertainty

    LMU Munich · Munich Center for Machine Learning (MCML) · DFKI (DSA)

  3. TRIAGE: Type-Routed Interventions via Aleatoric-Epistemic Gated Estimation in Robotic Manipulation and Adaptive Perception -- Don't Treat All Uncertainty the Same

    Mar 9, 2026Divake Kumar, Sina Tayebati, Devashri Naik +4Robotic ControlUncertainty Decomposition

    University of Illinois at Chicago · Intel Labs

  4. CREDO: Epistemic-Aware Conformalized Credal Envelopes for Regression

    Mar 6, 2026Luben M. C. Cabezas, Sabina J. Sloman, Bruno M. Resende +3Regression Prediction IntervalsConformal Prediction

    Department of Statistics, Federal University of S˜ao Carlos, S˜ao Carlos, Brazil · Institute of Mathematics and Computer Science , University of S˜ao Paulo, S˜ao Carlos, Brazil · Universit´e Grenoble Alpes, Inria, CNRS, Grenoble INP, LJK, France +1

  5. No Certificate, No Categorical Speech Act: A Brouwerian Assertibility Constraint for Public Reason

    Mar 4, 2026Michael JülichAI AccountabilitySelective Prediction

    aihorizon R&D, Munich, Germany.

  6. Can machines be uncertain?

    Mar 2, 2026Luis RosaEpistemic Uncertainty

    Washington University in St. Louis

  7. Instrumental and Proximal Causal Inference with Gaussian Processes

    Mar 2, 2026Yuqi Zhang, Krikamol Muandet, Dino Sejdinovic +2Proximal Causal InferenceCausal Inference

    Department of Statistics and Actuarial Science, University of Hong Kong, Hong Kong · Rational Intelligence Lab, CISPA Helmholtz Center for Information Security, Germany · Australian Institute for Machine Learning, Adelaide University, Australia +1

  8. Epistemic Gain, Aleatoric Cost: Uncertainty Decomposition in Multi-Agent Debate for Math Reasoning

    Mar 1, 2026Dan Qiao, Binbin Chen, Fengyu Cai +7Multi-Agent DebateEpistemic Uncertainty

    School of Data Science, The Chinese University of Hong Kong, Shenzhen, China · ByteDance, Beijing, China · Technical University of Darmstadt, Darmstadt, Germany +2

  9. Invariant Transformation and Resampling based Epistemic-Uncertainty Reduction

    Feb 26, 2026Sha HuInference-Time OptimizationTest-Time Augmentation

    Lund Research Center, Huawei Technologies Sweden AB, Sweden.

  10. Set-based v.s. Distribution-based Representations of Epistemic Uncertainty: A Comparative Study

    Feb 26, 2026Kaizheng Wang, Yunjia Wang, Fabio Cuzzolin +3Uncertainty QuantificationEpistemic Uncertainty

    College of Computing and Data Science, Nanyang Technological University, Singapore · Department of Computer Science, KU Leuven, Belgium · School of Engineering, Computing, and Mathematics, Oxford Brookes University, U.K. +1

  11. Not Just How Much, But Where: Decomposing Epistemic Uncertainty into Per-Class Contributions

    Feb 24, 2026Mame Diarra Toure, David A. StephensBayesian Neural NetworksClassification

    Department of Mathematics and Statistics , McGill University

  12. When Alpha Breaks: Two-Level Uncertainty for Safe Deployment of Cross-Sectional Stock Rankers

    Feb 24, 2026Ursina SanderinkQuantitative FinanceDecision-Making under Uncertainty

  13. Structure-Aware Epistemic Uncertainty Quantification for Neural Operator PDE Surrogates

    Feb 24, 2026Haoze Song, Zhihao Li, Mengyi Deng +4Uncertainty QuantificationEpistemic Uncertainty

    The Hong Kong University of Science and Technology (Guangzhou), Guangzhou, China · The Hong Kong University of Science and Technology, Hong Kong SAR, China

  14. ERA: Evidence-based Reliability Alignment for Honest Retrieval-Augmented Generation

    Feb 24, 2026Sunguk Shin, Meeyoung Cha, Byung-Jun Lee +1RAG RobustnessLLM Abstention

    Korea University, Seoul, South Korea · MPI-SP, Bochum, Germany · KAIST, Daejeon, South Korea +1

  15. Density-Informed Pseudo-Counts for Calibrated Evidential Deep Learning

    Feb 1, 2026Pietro Carlotti, Nevena Gligić, Arya FarahiEvidential Deep LearningOOD Detection

    Department of Statistics and Data Sciences University of Texas at Austin

  16. Uncertainty Quantification for Regression: A Unified Framework based on kernel scores

    Oct 29, 2025Christopher Bülte, Yusuf Sale, Gitta Kutyniok +1Uncertainty QuantificationAleatoric Uncertainty

    LMU Munich · 2Munich Center for Machine Learning (MCML) · 3DLR-German Aerospace Center +2

  17. Rethinking Prospect Theory for LLMs: Revealing the Instability of Decision-Making under Epistemic Uncertainty

    Aug 12, 2025Rui Wang, Qihan Lin, Jiayu Liu +7Prospect TheoryLLM Decision-Making

    Hong Kong University of Science and Technology · Huazhong University of Science and Technology · University of Illinois Urbana-Champaign

  18. Toward Efficient Uncertainty in LLMs through Evidential Knowledge Distillation

    Jul 24, 2025Lakshmana Sri Harsha Nemani, P. K. Srijith, Tomasz KuśmierczykLLM Uncertainty EstimationUncertainty-Aware Knowledge Distillation

    Department of Computer Science and Engineering, Indian Institute of Technology Hyderabad, India · Jagiellonian University, Faculty of Mathematics and Computer Science, Kraków, Poland

  19. CLEAR: Calibrated Learning for Epistemic and Aleatoric Risk

    Jul 10, 2025Ilia Azizi, Juraj Bodik, Jakob Heiss +1Uncertainty QuantificationAleatoric Uncertainty

    Department of Operations, HEC, University of Lausanne, Switzerland · BegooAI, Switzerland · Department of Statistics, University of California, Berkeley, USA +1

  20. Optimal Conformal Prediction under Epistemic Uncertainty

    May 25, 2025Alireza Javanmardi, Soroush H. Zargarbashi, Santo M. A. R. Thies +3Conformal PredictionConformal Risk Control

    1LMU Munich · 2MCML · 3CISPA +3

  21. An Axiomatic Assessment of Entropy- and Variance-based Uncertainty Quantification in Regression

    Apr 25, 2025Christopher Bülte, Yusuf Sale, Timo Löhr +3Uncertainty QuantificationAleatoric Uncertainty

    1LMU Munich · 2Munich Center for Machine Learning (MCML) · 3DLR-German Aerospace Center +2

  22. Prompting the Unknown: Understanding Response Uncertainty in Large Language Models

    Jul 20, 2024Ze Yu Zhang, Arun Verma, Finale Doshi-Velez +1LLM PromptingLLM Reliability

    Department of Computer Science, National University of Singapore, Republic of Singapore · Singapore-MIT Alliance for Research and Technology Centre · Harvard University

  23. Active Exploration via Autoregressive Generation of Missing Data

    May 29, 2024Tiffany Tianhui Cai, Hongseok Namkoong, Daniel Russo +1RL ExplorationAutoregressive Generation

    Department of Statistics Columbia University New York, NY 10025, USA · Decision, Risk, and Operations Division Columbia Business School New York, NY 10025, USA · Department of Mathematics Imperial College London London SW7 2AZ, United Kingdom