sft-data

Tag

Cards List
#sft-data

How to Fine-Tune a Reasoning Model? A Teacher-Student Cooperation Framework to Synthesize Student-Consistent SFT Data

Hugging Face Daily Papers ↗ · 2026-03-23 Cached

This paper introduces TESSY, a teacher-student cooperative framework for fine-tuning reasoning models that generates on-policy SFT data by decoupling generation into capability tokens (from teacher) and style tokens (from student), addressing catastrophic forgetting issues when using off-policy teacher data.

0 favorites 0 likes
← Back to home

Submit Feedback