SFT2 min read
Learning Style, Forgetting Semantics: A Case Study of SFT and RFT on Classification Tasks
Why does supervised fine-tuning (SFT) lead to more forgetting than reinforcement fine-tuning (RFT), even when all teacher demonstrations are semantically correct?
By Haodong Liang, Yanhao Jin, Krishnakumar Balasubramanian, Lifeng LaiarXiv - stat.ML
Read the full story
Originally published by arXiv - stat.ML on Oct 5, 2026.
Comments
Sign in to join the discussion.