What Should SFT Learn? Conditional Information Gain for Generalizable Post-Training
arXiv:2610.12995v1 Announce Type: cross Abstract: Supervised fine-tuning (SFT) remains a widely used approach for post-training large language models, because fixed demonstrations can directly introduce desired reasoning strategies and behavioral patterns. Yet forcing a model to imitate externally provided trajectories may also interfere with behaviors already supported by pretraining, limiting generalization beyond the training distribution. Recent dynamic SFT methods mitigate this issue by re…