AI RESEARCH
Overtrained, Not Misaligned
arXiv CS.AI
•
ArXi:2605.12199v1 Announce Type: cross Emergent misalignment (EM), where fine-tuning on a narrow task (like insecure code) causes broad misalignment across unrelated domains, was first nstrated by Betley. 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.