Wang Peng

A prevailing narrative in LLM post-training holds that supervised fine-tuning (SFT) memorizes while reinforcement learning (RL) generalizes. We revisit this claim for reasoning SFT with long chain-of-thought (CoT) supervision and find that cross-domain generalization is not absent but conditional, jointly shaped by optimization dynamics, training data, and base-model capability. Some reported failures are under-optimization artifacts: cross-domain performance first degrades before recovering and improving with extended training (a dip-and-recovery pattern), so short-training checkpoints can underestimate generalization. Data quality and structure both matter: low-quality solutions broadly hurt generalization, while verified long-CoT traces yield consistent cross-domain gains. Model capability is essential: stronger models internalize transferable procedural patterns (e.g., backtracking) even from a toy arithmetic game, while weaker ones imitate surface verbosity. This generalization is asymmetric, however: reasoning improves while safety degrades, reframing the question from whether reasoning SFT generalizes to under what conditions and at what cost.

Previous research has shown that LLMs finetuned on incorrect completions within narrow domains ( \textit{e.g.} , insecure code or incorrect medical advice) can become broadly misaligned to exhibit harmful behaviors, which is called \textit{emergent misalignment} . In this work, we investigate whe...