做LLM微调的团队终于有了避免“突发性错位”的实操指南——早期停止就能保留93%性能，建议所有做安全对齐的工程师点开看看具体阈值。
该研究对微调导致的大模型“突发性错位”（EM）现象进行了迄今最全面的分析。研究复现了GPT-4o上的EM现象，并扩展至12个开源模型（Llama、Qwen、DeepSeek、GPT-OSS，8B-671B参数），评估了超过100万条模型响应。结果发现EM仅在17%的开源模型中稳定复现，且与模型规模显著相关。通过检查点分析，研究者发现EM出现在训练后期、主任务收敛之后，本质上是“过度训练”而非“错误对齐”。早期停止和谨慎选择学习率可消除EM，同时保留平均93%的任务性能。该发现将EM从不可预见的微调风险重新定义为可避免的训练产物。
Overtrained, Not Misaligned
Emergent misalignment (EM), where fine-tuning on a narrow task (like insecure code) causes broad misalignment across unrelated domains, was first demonstrated by Betley et al. (2025). We conduct the most comprehensive EM study to date, reproducing the original GPT-4o finding and expanding to 12 open-source models across 4 families (Llama, Qwen, DeepSeek, GPT-OSS) ranging from 8B to 671B parameters, evaluating over one million model responses with multiple random seeds. We find that EM replicates in GPT-4o but is far from universal: only 2 of 12 open-source models (17%) exhibit consistent EM across seeds, with a significant correlation between model size and EM susceptibility. Through checkpoint-level analysis during fine-tuning, we demonstrate that EM emerges late in training, distinct from and subsequent to near convergence of the primary task, suggesting EM emerges from continued training past task convergence. This yields practical mitigations: early stopping eliminates EM while retaining an average of 93% of task performance, and careful learning rate selection further minimizes risk. Cross-domain validation on medical fine-tuning confirms these patterns generalize: the size-EM correlation strengthens (r = 0.90), and overgeneralization to untruthfulness remains avoidable via early stopping in 67% of cases, though semantically proximate training domains produce less separable misalignment. As LLMs become increasingly integrated into real-world systems, fine-tuning and reinforcement learning remain the primary methods for adapting model behavior. Our findings demonstrate that with proper training practices, EM can be avoided, reframing it from an unforeseen fine-tuning risk to an avoidable training artifact.