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 2verdicts
UNVERDICTED 2representative citing papers
DiDi-Merging achieves dynamic model merging performance matching or exceeding prior methods while using only 1.24x to 1.4x the parameters of a single fine-tuned model.
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.
-
Dynamic Model Merging Made Slim
DiDi-Merging achieves dynamic model merging performance matching or exceeding prior methods while using only 1.24x to 1.4x the parameters of a single fine-tuned model.