This paper studies the problem of aggregating calibrated Bayesian experts into a new calibrated expert.

This paper studies the behavior of mixture-of-experts (MoE) models under distribution shift and proposes an adversarial reweighting method to improve their calibration.

The paper introduces CalArena, a large-scale, standardized benchmark covering nearly 2000 experiments to comprehensively evaluate post-hoc calibration methods, finding that smooth calibration function…

The paper formalizes the concept of calibration for probabilistic label ranking, demonstrating that popular models are often poorly calibrated and that calibration captures a meaningful quality dimens…

This paper develops statistical learning theory for gradient boosting in Peaks-over-Threshold modeling using Generalized Pareto distributions, deriving error bounds and reducing gradient correlation.

The paper proposes Under-Cali, an uncertainty-driven dual-expert calibration framework, to achieve stable and efficient online forecasting for irregularly sampled multivariate time series.

The paper proposes a finite-calibration regime map to determine the optimal calibration method (low-dimensional stackers vs. joint tables) for LLM judge panels given limited human labeling budgets, sh…

The paper proposes CAGE-CAL, a counterfactual graph calibration framework, to accurately assess the reliability and detect over-confidence in multi-agent LLM systems after agents communicate.

This paper evaluates the effectiveness of Bayesian workflow for verifying statistical correctness of probabilistic programs written by language models, and compares it to unit tests and no feedback.

The paper introduces FORCEBENCH, a new stress test designed to evaluate whether cited sources genuinely warrant the strength of a claim, revealing that standard citation evaluation methods often fail…

The paper introduces a novel framework to quantify faithful confidence expression (FC) in Large Reasoning Models (LRMs), finding that FC remains a significant and challenging reliability target for th…

This paper measures the impact of procedural skills on LLM agents, distinguishing between improvements and regressions, and identifies causes of regression.

This paper proposes a simple real-time monitor for LLMs that turns an external verifier signal into an alarm decision by thresholding, showing competitiveness with advanced monitors in mathematical re…

CALIBURN introduces a novel, five-component streaming pipeline for intrusion detection that allows operators to specify alerting behavior using cost and budget constraints, achieving state-of-the-art…

The paper proposes DAMEL, a dual-axis multi-expert learning algorithm that simultaneously reduces both prediction bias and variance in class-imbalanced learning by leveraging multiple experts across b…

The paper proposes a trust schema and verification framework to ensure that agent skills, which augment LLMs, are rigorously verified before deployment, thereby making human-in-the-loop oversight scal…