Epistemic Uncertainty

Follow this topic Ask about this topic

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

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

Attribution and Uncertainty Behavior of Learned Residual Gyro Correction for Gyro-Stellar Estimation
Jul 27, 2026Mariela De Lucas Álvarez, Melvin Laux, Arthur de Freitas Precht +4Spacecraft Attitude Determination Residual Learning
Robotics Innovation Center, German Research Center for AI (DFKI GmbH), Bremen, Germany · Airbus Defence and Space GmbH, Immenstaad, Germany
Controllable Diversity in Normalization-Based Implicit Ensembles via Softmax-Temperature Modulation
Jul 26, 2026Mihai Suteu, Ovidiu SerbanEnsemble Learning Ensemble Diversity
Data Science Institute, Imperial College London
From Hybrid Mechanistic--Data-Driven Modeling Toward Neuro-Symbolic AI: What, Why, and How
Jul 24, 2026Moein E. Samadi, Andreas SchuppertNeuro-Symbolic AI Epistemic Uncertainty
Institute for Computational Biomedicine, RWTH Aachen University, Aachen, Germany. · Center for Computational Life Sciences, RWTH Aachen University, Aachen, Germany.
Explainable Belief Harmonization under Dynamic Epistemic Partitions
Jul 23, 2026Adam Kostka, Jarosław A. ChudziakBelief Revision Dynamic Epistemic Logic
Warsaw University of Technology · Warsaw University of Technology, Warsaw, Poland
Bayesian uncertainty estimation improves clinical decision making in medical AI agents
Jul 22, 2026Frederik Hauke, Patrick Wienholt, Christiane Kuhl +4Clinical Decision Support Clinical Decision-Making
Department of Diagnostic and Interventional Radiology, University Hospital RWTH Aachen, Aachen, Germany. · Department of Medical Oncology, National Center for Tumor Diseases (NCT), Heidelberg University Hospital, Heidelberg, Germany. · Else Kröner Fresenius Center for Digital Health, TU Dresden, Dresden, Germany. +1
Disentangling Model and Human Data Uncertainty in Apparent Facial Age Estimation
Jul 17, 2026Andrei Foitos, Ivo Pascal de Jong, Matias Valdenegro-ToroBayesian Neural Networks Uncertainty Quantification
Bernoulli Institute, University of Groningen, Groningen, NL
Subjective Risk Decomposition: A New View for Uncertainty Quantification
Jul 16, 2026Raghad Alamri, Michele Caprio, Gavin BrownUncertainty Quantification Aleatoric Uncertainty
Department of Computer Science, The University of Manchester · Department of Computer Science, University of Warwick
Evaluating Epistemic Uncertainty: Beyond OOD Detection and Active Learning
Jul 16, 2026Jakub Paplhám, Willem Waegeman, Eyke Hüllermeier +1Selective Prediction Decision-Making under Uncertainty
Czech Technical University in Prague · Ghent University · LMU Munich, MCML, DFKI
Decision Making Needs Uncertainty Quantification [Lecture Notes]
Jul 15, 2026Osvaldo SimeoneUncertainty Quantification Decision-Making under Uncertainty
Institute for Intelligent Networked Systems, Northeastern University London, One Portsoken Street, London, E1 8PH, UK
EvidentialRAG: Quantifying and Mitigating Information Conflict in Multi-Source Retrieval-Augmented Generation via Evidential Deep Learning
Jul 11, 2026S M Asif Hossain, Ruksat Khan Shayoni, M. F. MridhaRetrieval-Augmented Generation Evidential Deep Learning
aSchool of Computing, Wichita State University, Kansas, USA · bDepartment of Computer Science, American International University-Bangladesh, Dhaka, Bangladesh
Heckman-Corrected Epistemic Uncertainty: Selection on Unobservables Defeats Importance Weighting
Jul 7, 2026Gunner Levi HoweSelection Bias Uncertainty Calibration
Independent Researcher
Trading Confidence: Comprehensive Uncertainty Estimation in Algorithmic Trading
Jul 3, 2026Lin Li, Li Rong Wang, Hsuan Fu +1Reinforcement Learning Uncertainty Quantification
Nanyang Technological University 50 Nanyang Avenue, Singapore · Nanyang Technological University Centre for Frontier AI Research, A*STAR 50 Nanyang Avenue, Singapore · Laval University Quebec, Canada
Who Determines the Meaning of an Emotion? Affective Sovereignty as an Epistemic Consequence of Measurement Limits
Jun 30, 2026Keito InoshitaHuman Oversight of AI Emotion Recognition
Faculty of Business and Commerce, Kansai University, 3-3-35 Yamate-cho, Suita, 564-8680, Osaka, Japan.
When Certainty Is an Artifact: Keyword Lexicon Blindness and the (Mis)Measurement of Rhetorical Stance
Jun 24, 2026Bo ChenStance Detection Sentiment Analysis
Institute of Computing Technology, Chinese Academy of Sciences
Interpretable Uncertainty Routing Separating Emotion Ambiguity from Distribution Shift in Facial Expression Recognition
Jun 21, 2026Keito Inoshita, Takato UenoUncertainty Quantification Selective Prediction
Faculty of Business and Commerce, Kansai University, Suita, Japan · Data Science and AI Innovation Research Promotion Center, Shiga University, Hikone, Japan · Graduate School of Data Science, Shiga University, Hikone, Japan
Perturbation-Based Epistemic Uncertainty for Failure Detection in Vision-Language-Action Models
Jun 18, 2026Yousung Lee, Dongsoo HarFailure Detection for VLA Models Uncertainty Estimation for VLA Models
Korea Advanced Institute of Science and Technology (KAIST), Daejeon, Republic of Korea.
On the QUEST for Uncertainty Quantification via Highest Density Regions
Jun 17, 2026Sam Goring, Tom Kuipers, Nicola Paoletti +1Uncertainty Quantification Aleatoric Uncertainty
King’s College London · Northeastern University London
LLM Doesn't Know What It Doesn't Know: Detecting Epistemic Blind Spots via Cross-Model Attribution Divergence on Clinical Tabular Data
Jun 17, 2026Akshat Dasula, Prasanna Desikan, Jaideep SrivastavaLanguage Model Calibration LLM Uncertainty Estimation
Centific AI Research · Department of Computer Science & Engineering, University of Minnesota-Twin Cities, Minneapolis, USA.
Hybrid Uncertainty Sensitivity Analysis Based on the HSIC for High-Dimensional Responses with Aleatory--Epistemic Separation
Jun 12, 2026Shijie Zhong, Jiangfeng Fu, Pengfei WeiUncertainty Quantification Aleatoric Uncertainty
School of Power and Energy Northwestern Polytechnical University Xi’an, Shanxi 710129
Exposure Bias as Epistemic Underidentification in Recursive Forecasting
Jun 11, 2026Riku Green, Zahraa S. Abdallah, Telmo M Silva FilhoDistribution Shift Time Series Forecasting
University of Bristol, UK
Epistemic Uncertainty Is Not the Reducible Kind
Jun 10, 2026Robin YoungUncertainty Quantification Uncertainty Decomposition
University of Cambridge
What Uncertainties Do We Need for Dynamical Systems?
Jun 10, 2026Yusuf Sale, Christopher Bülte, Felix Czaja +2Dynamical Systems Uncertainty Quantification
Institute of Computer Science, LMU Munich · Munich · Department of Mathematics, LMU Munich +1
Can we trust our models? Epistemic calibration in second-order classification
Jun 9, 2026Arthur HoarauUncertainty Quantification Uncertainty Calibration
Université de Lorraine, CentraleSupélec · Loria, CNRS, Metz, France
On the evolution of the concept of probability as a mirror of the evolution of reason
May 26, 2026Jean-Louis Le Mouël, Vincent Courtillot, Dominique Gibert +6Scientific Reasoning Epistemic Uncertainty
Acad´emie des Sciences, Institut de France, Paris, France · DeepField Sensing, France · Institute of Earthquake Prediction Theory and Mathematical Geophysics, Russian Academy of Sciences, Moscow, Russia +4
Breaking the Epistemic Trap: Active Perception Under Compound Uncertainty
May 26, 2026Chayan Banerjee, Ethan GoanActive Perception Constrained RL
School of Electrical Engineering and Robotics, Queensland University of Technology, Brisbane, Australia.
Generalized Evidential Deep Learning: From a Bayesian Perspective
May 25, 2026Yuanye Liu, Yibo Gao, Yuanyang Chen +1Evidential Deep Learning Uncertainty Quantification
School of Data Science, Fudan University, Shanghai, China.
On the Epistemic Uncertainty of Overparametrized Neural Networks
May 24, 2026David RügamerBayesian Neural Networks Overparameterized Neural Network
Department of Statistics, LMU Munich, Munich, Germany · Munich Center for Machine Learning (MCML), Munich, Germany
Breaking the Chains of Probability: Neutrosophic Logic as a New Framework for Epistemic Uncertainty in Large Language Models
May 22, 2026Maikel Yelandi Leyva-Vázquez, Florentin SmarandacheLLM Evaluation Knowledge Conflicts in Language Models
Universidad Bolivariana del Ecuador, Coordinación Académica de Posgrado, Durán, Ecuador · Universidad de Guayaquil, Guayaquil, Ecuador · Universidad Bernardo O’Higgins, Santiago, Chile +1
Do Deep Ensembles Actually Capture Uncertainty in Graph Neural Networks?
May 21, 2026Pedro C. Vieira, Pedro Ribeiro, Viacheslav BorovitskiyGraph Neural Networks Deep Ensembles
University of Edinburgh · DCC/FCUP, University of Porto
A Posterior-Predictive Variance Decomposition for Epistemic and Aleatoric Uncertainty in Wind Power Forecasting
May 21, 2026Yinsong Chen, Samson S. Yu, Kashem M. MuttaqiUncertainty Quantification Time Series Forecasting
School of Engineering, Deakin University, Melbourne, VIC 3216, Australia · ARC Training Centre in Energy Technologies for Future Grids, School of Engineering, University of Wollongong, Wollongong, NSW 2522, Australia

Jul 27, 2026J/K move · Enter open · S save

Attribution and Uncertainty Behavior of Learned Residual Gyro Correction for Gyro-Stellar Estimation

Mariela De Lucas Álvarez, Melvin Laux, Arthur de Freitas Precht, Maurice Martin+3

Robotics Innovation Center, German Research Center for AI (DFKI GmbH), Bremen, Germany · Airbus Defence and Space GmbH, Immenstaad, Germany

Spacecraft Attitude Determination Residual Learning Aleatoric Uncertainty Inertial Navigation Epistemic Uncertainty

Open paper AskPDF arXiv

This work investigates uncertainty decomposition and explainability in a deep learning-based framework for gyroscope bias correction. A 1-D Convolutional Neural Network is trained to predict residual angular rate corrections from multi-sensor inputs, including gyroscope and star tracker measurements. The bias corrections are sent to a flight-representative Gyro-Stellar Estimator. The network produces both mean corrections and input-dependent (heteroscedastic) aleatoric uncertainty, while epistemic uncertainty is estimated via an ensemble of independently trained models. The proposed approach is trained under nominal conditions and evaluated in both nominal and structured perturbations that include additive and temporally correlated noise. Gradient-based attribution methods are applied to both the correction and uncertainty outputs, enabling a decomposition of the evidence that drives state updates and uncertainty estimates. By aggregating attribution patterns across rotational axes and regimes, we reveal axis-specific behaviors and characterize how structured perturbations influence the collaboration between aleatoric and epistemic uncertainty. Uncertainty analysis shows that aleatoric uncertainty increases with perturbation intensity, but the distributions overlap and the calibration is not consistent across regimes. On the other hand, epistemic uncertainty gives a clear signal that gets clearer as the distributional shift happens, showing that the models disagree more. These results show that aleatoric and epistemic uncertainty work well together and that epistemic uncertainty is better at distinguishing between nominal and perturbed operating conditions. The results provide insight into the behavior of hybrid learning-based state estimation components and motivate the use of uncertainty for downstream monitoring and fault detection.