Uncertainty quantification for trustworthy deep learning: Methods and measures
H. Martin Gillis, Thomas Trappenberg
stat.ML, cs.LG
Submitted: 2026-07-30
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- A Primer on Bayesian Neural Networks: Review and Debates
- SCOPE: Selective Conformal Optimized Pairwise LLM Judging
- On Last-Layer Algorithms for Classification: Decoupling Representation from Uncertainty Estimation
- Learning Confidence for Out-of-Distribution Detection in Neural Networks
- A Survey of Uncertainty Estimation in LLMs: Theory Meets Practice
- Combining Model and Parameter Uncertainty in Bayesian Neural Networks
- Language Models (Mostly) Know What They Know
- A Simple Unified Framework for Detecting Out-of-Distribution Samples and Adversarial Attacks
- Why M Heads are Better than One: Training a Diverse Ensemble of Deep Networks
- Understanding Measures of Uncertainty for Adversarial Example Detection
Related papers
- Behavior of prediction performance metrics with rare events
- Optimal Estimation of Generic Dynamics by Path-Dependent Neural Jump ODEs
- A Posterior-Dynamics Framework for Imaging Inverse Problems with Pretrained Diffusion Priors
- Scalable Posterior Uncertainty for Flexible Density-Based Clustering
- A Transport Geometry of Benign Overfitting
- Efficient quadratic entropy with distance sketches