AI RESEARCH
Probability-Entropy Calibration: An Elastic Indicator for Adaptive Fine-tuning
arXiv CS.AI
•
ArXi:2602.01745v2 Announce Type: replace-cross Token-level reweighting is a simple yet effective mechanism for controlling supervised fine-tuning, but common indicators are largely one-dimensional: the ground-truth probability reflects downstream alignment, while token entropy reflects intrinsic uncertainty induced by the pre-