epistemic-uncertainty

Tag

Cards List
#epistemic-uncertainty

Tracing sources of epistemic uncertainty in deep learning predictions: homo- and hetero-scedastic linearized estimators

arXiv cs.LG · 2026-08-11 Cached

The paper adapts classical statistical estimators to deep learning for tracing epistemic uncertainty into aleatoric and data-scarcity sources, leveraging approximate Fisher Information Matrices for scalability.

0 favorites 0 likes
#epistemic-uncertainty

A Unified Risk View of Uncertainty: Posterior Risk for Disentanglement and Evaluation Beyond Proxies

arXiv cs.LG · 2026-08-07 Cached

This paper proposes a unified definition of uncertainty as pointwise posterior risk and introduces a theory-backed benchmark using semi-synthetic datasets to directly compute oracle epistemic and aleatoric uncertainty, enabling fine-grained evaluation beyond proxy tasks.

0 favorites 0 likes
#epistemic-uncertainty

From Hybrid Mechanistic--Data-Driven Modeling Toward Neuro-Symbolic AI: What, Why, and How

arXiv cs.LG · 2026-07-28 Cached

This paper introduces the Hybrid-to-NeSy (H2N) framework, which systematically translates hybrid mechanistic-data-driven models into neuro-symbolic AI designs, enabling the derivation of metrics for structural violation and belief dispersion as measures of epistemic uncertainty in the mechanistic part.

0 favorites 0 likes
#epistemic-uncertainty

Heckman-Corrected Epistemic Uncertainty: Selection on Unobservables Defeats Importance Weighting

arXiv cs.LG · 2026-07-08 Cached

This paper introduces Heckman-corrected epistemic uncertainty to address selection on unobservables in machine learning, demonstrating that importance weighting fails when selection depends on unobservables correlated with outcomes. The method restores calibration in controlled experiments and real data, outperforming standard UQ baselines.

0 favorites 0 likes
#epistemic-uncertainty

Who Determines the Meaning of an Emotion? Affective Sovereignty as an Epistemic Consequence of Measurement Limits

arXiv cs.AI · 2026-07-01 Cached

This paper introduces the concept of the 'Affectosphere' and argues that emotion AI cannot fully determine the meaning of an individual's emotion due to irreducible uncertainty, leading to the norm of 'affective sovereignty' where the experiencing subject retains final interpretive authority.

0 favorites 0 likes
#epistemic-uncertainty

LLM Doesn't Know What It Doesn't Know: Detecting Epistemic Blind Spots via Cross-Model Attribution Divergence on Clinical Tabular Data

arXiv cs.AI · 2026-06-20 Cached

This paper explores Large Language Models' inability to recognize their knowledge limits on structured clinical data, proposing a cross-model attribution divergence method to detect epistemic blind spots. The approach improves calibration and accuracy without training by combining few-shot examples and SHAP-derived feature evidence.

0 favorites 0 likes
#epistemic-uncertainty

Evolving Robustness--Exploration Trade-off in Online Reinforcement Learning via Quantile Bayesian Risk MDPs

arXiv cs.LG · 2026-05-26 Cached

This paper proposes a quantile Bayesian risk-aware MDP framework for online RL that adaptively balances robustness and exploration over time, providing theoretical regret bounds and demonstrating strong empirical performance.

0 favorites 0 likes
#epistemic-uncertainty

Breaking the Chains of Probability: Neutrosophic Logic as a New Framework for Epistemic Uncertainty in Large Language Models

arXiv cs.AI · 2026-05-26 Cached

This paper investigates Neutrosophic Logic as a framework for modeling epistemic states in Large Language Models, demonstrating that it can capture 'hyper-truth' states beyond traditional probability constraints, leading to more transparent and ethically aware AI systems.

0 favorites 0 likes
#epistemic-uncertainty

MMD-Balls as Credal Sets: A PAC-Bayesian Framework for Epistemic Uncertainty in Test-Time Adaptation

arXiv cs.LG · 2026-05-22 Cached

This paper develops a PAC-Bayesian framework for test-time adaptation that uses MMD-balls as credal sets, providing formal generalization bounds and separating epistemic from aleatoric uncertainty under distribution shift.

0 favorites 0 likes
#epistemic-uncertainty

Don't Collapse Your Features: Why CenterLoss Hurts OOD Detection and Multi-Scale Mahalanobis Wins

arXiv cs.LG · 2026-05-22 Cached

This paper introduces GOEN, a pipeline combining multi-scale features, L2 normalization, and Mahalanobis distance for OOD detection, and finds that CenterLoss regularization actually degrades OOD performance despite improving classification accuracy.

0 favorites 0 likes
#epistemic-uncertainty

A better method for identifying overconfident large language models

MIT News — Artificial Intelligence · 2026-03-19 Cached

MIT researchers developed a new method for identifying overconfident LLMs by measuring cross-model disagreement across similar models, rather than relying solely on self-consistency metrics. This approach better captures epistemic uncertainty and more accurately identifies unreliable predictions in high-stakes applications.

0 favorites 0 likes
← Back to home

Submit Feedback