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

116 papers4 papers in the last four weeks, down 69% on the four weeks before. 0.0% of all new papers.

  1. The Posterior-Prior Epistemic Gap: When World Model Imagination Fails to Carry Task-Relevant Signals

    Nov 11, 2026Jaerock Kwon, Elahe Delavari, Donghyun Kim +1World Model-Based PlanningAutonomous Driving Planning

  2. Role-based Effectiveness of an Epistemic Uncertainty Estimate in Training Models for Semantic Segmentation of 3D LiDAR Point Clouds

    Nov 3, 2026Krishnakumar N, Jaya Sreevalsan-Nair3D Semantic SegmentationSegmentation Uncertainty Estimation

  3. Specification-Aware Predictive Uncertainty Decomposition

    Nov 2, 2026Roman Vashurin, Mikhail Seleznyov, Assel Yermekova +7Uncertainty DecompositionLLM Uncertainty Estimation

  4. Conditional Flow Models Convert Epistemic Uncertainty into Apparent Aleatoric Variance

    Oct 21, 2026Navodita Sharma, Abhishek Shetty, Max Simchowitz +1Conditional Flow MatchingConditional Distribution Estimation

  5. What "Form'' of Uncertainty Does Conformal Prediction Quantify?

    Oct 17, 2026Soroush H. Zargarbashi, Mohammad Sadegh Akhondzadeh, Rebekka Burkholz +1Conformal PredictionEpistemic Uncertainty

  6. Trust Before Autonomy: Rethinking Agentic Remote Sensing for Crisis Response

    Oct 13, 2026Georgios Angelidis, Aggelos Psiris, Spyridon Evangelatos +4Agent ReliabilityRemote Sensing

  7. Vision: "What Don't I Know About User's Preferences?" How Uncertainty Estimation Improves Proactive Assistant Alignment

    Oct 11, 2026Zhiyu An, Ziyi Xuan, Yu Yang +1Proactive AgentsUser Preference Modeling

  8. Accurate but Not Humble: Evaluating Epistemic Humility in LLM Agents under Knowledge Conflict

    Oct 8, 2026Kaiser Sun, Bernal Jimenez Gutierrez, Hongjun Liu +4LLM Agent EvaluationEpistemic Uncertainty

  9. Addressing Overcommitment in the Reasoning of Gendered Economic Memes under Multimodal Ambiguity

    Oct 8, 2026Kushal Kanwar, Dushyant Singh Chauhan, Kapil Rana +2Multimodal Meme ClassificationMultimodal Understanding

  10. Epistemic Uncertainty-Aware Defect Detection for Quality Control in Medical Device Manufacturing

    Oct 6, 2026Raham A. Butt, Marco Romanelli, Roche C. de GuzmanSelective PredictionEpistemic Uncertainty

  11. Evaluation of Active Feature Acquisition Policies with Tabular Foundation Models

    Oct 5, 2026Yuta Kobayashi, Divyam Madaan, Shalmali JoshiOff-Policy EvaluationValue Function Estimation

  12. Rethinking Epistemic Uncertainty in Node Classification through Information Growth

    Oct 2, 2026Emma Meneghini, Francesco Ferrini, Bruno Lepri +2Epistemic UncertaintyEvidential Deep Learning

  13. Revealing Epistemic Uncertainty in MLLMs via Causal-Invariant Masking

    Oct 2, 2026Haoyang Luo, Linwei Tao, Jie Gui +4LLM Uncertainty EstimationEpistemic Uncertainty

  14. Structural Limits of the Information-Theoretic Uncertainty Decomposition

    Sep 30, 2026Jakob Lønborg Christensen, Christian F. Baumgartner, Morten Rieger Hannemose +2Aleatoric UncertaintyInformation-Theoretic Lower Bounds

  15. Epistemic Learning from Imprecise Annotation

    Sep 28, 2026Kaizheng Wang, Siu Lun ChauSoft-Label LearningEpistemic Uncertainty

  16. Adaptive Rollout Truncation Based on Epistemic Uncertainty for Efficient Offline World Model Training

    Sep 18, 2026Nikodem Sebastian Zymla, Laurin Thiele, Johannes PitzWorld Model LearningWorld Models for Robotics

  17. Uncertainty-Aware End-to-End AI Weather Forecasting: Disentangling Observation and Model Contributions

    Aug 31, 2026Rodrigo Almeida, Noelia Otero, Jost Arndt +3Probabilistic ForecastingAleatoric Uncertainty

  18. Beyond Local Surprise: Grounded Dialogue as Selective Belief Revision under Referential Uncertainty

    Aug 26, 2026Ziming Liu, Bhanu Chaitanya Jasti, Ziyang Xu +3Belief RevisionMulti-Turn Dialogue Evaluation

  19. SPARC: Single-Pass Scaling for Motion Forecasting with Conformal Bayesian Last Layers

    Aug 21, 2026Sakif Hossain, Julian Teusch, Jörg P. MüllerHuman Motion PredictionUncertainty Calibration

  20. Robust Risk Under Evolving Uncertainty: A Wasserstein Counterpart of the Entropic Value-at-Risk

    Aug 19, 2026Deep Kumar Ganguly, Jan KřetínskýRisk-Sensitive RLWasserstein Distributionally Robust Optimization

  21. LLMs Don't Pay for the Jump

    Aug 14, 2026Paras Balani, Subhrakanta PandaAbductive Reasoning in Language ModelsAbductive Reasoning

  22. TRAPSBench: Vision-Language Models Encode but Fail to Express Epistemic Restraint

    Aug 13, 2026Fnu Pramono, John Cai, Sourabh KulkarniVLM EvaluationAbstention in VLMs

  23. A Ground-Truth Framework for Uncertainty Disentanglement with Posterior Risk

    Aug 6, 2026Frieder Wizgall, Georg Tirpitz, Moritz Seiler +2Uncertainty QuantificationAleatoric Uncertainty

  24. Bayesian Expected Uncertainty Reduction (B-EUR) Model: A Computational Account of What Makes Design Options Worth Trying

    Aug 6, 2026Shimon Honda, Takuma Miyaguchi, Koji Koizumi +3Computational Cognitive ModelingValue of Information