AIIC AI Intelligence Centre

SOURCE-LINKED INTELLIGENCE

SupportCal: Label-Free Calibration of Post-Trained LLMs via Reference Support and Corroboration

arXiv · AI, language, vision and robotics · article · Sep 21, 2026 · UTC

Post-training often improves task performance but can degrade confidence calibration, leaving post-trained language models (PoLMs) more overconfident than their corresponding pretrained language models (PLMs). Because task-specific labeled calibration data can be costly or unavailable, the corresponding pretrained PLM provides a natural label-free reference for post-hoc calibration. Prior agreement-gated PLM-referenced calibration fits a scalar temperature using only examples on which the PoLM and its PLM reference agree, excluding disagreement examples because direct alignment can drive the f

Read original source ↗ Open in workspace

recordType
paper
region
Global

Evidence & attribution

First collected: 2026-09-23T08:01:43.213Z. This is not the publication date.