最新资讯

言栖资讯收录 195425 篇 AI、开发与建站文章,按发布时间排序,支持搜索与按语言筛选。

Persona-Model Collapse in Emergent Misalignment

Persona-Model Collapse in Emergent Misalignment

arXiv:2605.12850v3 Announce Type: replace-cross Abstract: Fine-tuning large language models on narrow data with harmful content produces broadly misaligned beha…

EnglisharXiv cs.CR