Why Constrained Updates Still Forget: A Functional-Path Analysis of Continual SFT
arXiv:2610.30191v1 Announce Type: new Abstract: 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 intervenin…
Read the full story at arXiv stat.ML ↗
Timeline · 1 report
- 2026-10-23 04:00 · arXiv stat.ML
Why Constrained Updates Still Forget: A Functional-Path Analysis of Continual SFT