BLAST RADIUS

Open-weight & owned stack · Training tuning

Researchers Stabilize LLM Supervised Fine-Tuning

Sep 13, 2026

A paper proposes explicit distributional control during supervised fine-tuning to reduce catastrophic forgetting while improving target-task performance.

Read the original at awesomepapers.ioOpens the publisher's site in a new tab

More in Open-weight & owned stack