1
Emergent alignment and the projectability of ethical personas
发现大模型微调后涌现对齐现象，探讨伦理人格的可投射性，关乎AI安全前沿突破。
arXiv:2606.09475v1 Announce Type: cross Abstract: Work on `emergent misalignment' shows that finetuning LLMs on narrow tasks can induce broadly misali…