Calibration and Risk-Budgeted Decisions with System One Models

arXiv:2610.19811 · stat.ML, cs.LG · Submitted 2026-10-14 · Read on arXiv

stat.ML, cs.LG

Submitted: 2026-10-14

Updated: 2026-10-14

Code: https://github.com/jaredpalmer/kev

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Calibration — 1× in this paper · explained in 9 episodes

Sources

• AEGIS: Online Adaptive AI Content Safety Moderation with Ensemble of LLM Experts
• Safety-Flag: A Unified Benchmark for the Reliability and Calibration of LLM Content Moderators
• Language Models (Mostly) Know What They Know
• Beyond Calibration: Do a Typed-Decision Model's Probabilities Obey the Probability Axioms?
• Measuring Calibration in Deep Learning
• Qwen3Guard Technical Report

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