SFT2 min read
Why Constrained Updates Still Forget: A Functional-Path Analysis of Continual SFT
Supervised fine-tuning adapts language models to specialized tasks but can disrupt previously acquired behavior. Existing approaches constrain parameters, gradients, or replay objectives, yet the connection between the protected object, the intervening trajectory, and retained outputs remains…
By Qingsen Ma, Dianyun Wang, Jiahong Liu, Irwin KingarXiv - stat.ML
Read the full story
Originally published by arXiv - stat.ML on Oct 23, 2026.
Comments
Sign in to join the discussion.