A diagnostic framework discovers prevalent input-dependent calibration heterogeneity in LLMs via a calibration-aware representation and kernel-smoothed signed miscalibration field, enabling local corrections that outperform global methods like temperature scaling in miscalibrated regions.
Title resolution pending
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.LG 2years
2026 2representative citing papers
FairHealth is a modular Python library that integrates fairness metrics, encrypted federated learning, and low-bandwidth explainability for trustworthy healthcare AI in low-income countries.
citing papers explorer
-
Discovery of Hidden Miscalibration Regimes
A diagnostic framework discovers prevalent input-dependent calibration heterogeneity in LLMs via a calibration-aware representation and kernel-smoothed signed miscalibration field, enabling local corrections that outperform global methods like temperature scaling in miscalibrated regions.
-
FairHealth: An Open-Source Python Library for Trustworthy Healthcare AI in Low-Resource Settings
FairHealth is a modular Python library that integrates fairness metrics, encrypted federated learning, and low-bandwidth explainability for trustworthy healthcare AI in low-income countries.