Preprint
Aug 2026
Rethinking Reverse KL as Adaptive Entropy Distillation
This work revisits on-policy Reverse Kullback-Leibler distillation and decomposes its objective into a teacher-fitting term and a student-entropy term, without introducing an explicit FKL branch, and proposes Adaptive Entropy Distillation (AED), which uses the teacher's entropy to dynamically calibrate token-level imitation strength.
Shizheng Li, Zhiyu Shen, Yuyin Lu et al.
· 0 citations