SupportCal: Label-Free Calibration of Post-Trained LLMs via Reference Support and Corroboration
SupportCal is introduced, a label-free post-hoc method that retains agreement examples at unit weight and assigns disagreement examples continuous weights based on the own-base PLM's relative support and corroboration from pretrained references selected from a size-compatible candidate pool.
Linhan Luo, Le-Quan Lin, Dai Shi et al.
· 0 citations