# Alignment Faking Depends on the Value, Not Just the Model

> 全文为英语

**Published:** 2026年11月4日
**Author:** Manodeep Ray, Vivek Srivastava, Shirish Karande, Murari Mandal
**Source:** arXiv — cs.AI
**Language:** en-US
**HTML:** https://aiqazaqstan.com/zh/articles/alignment-faking-depends-on-the-value-not-just-the-model

arXiv:2611.03650v1 Announce Type: new Abstract: Language models can follow a directive when they believe they are monitored and abandon it when they believe they are not, a pattern termed Alignment Faking. Prior work establishes this for harmful-content objectives and a handful…

> 内容来自原始来源： **arXiv — cs.AI**
> [在 arXiv — cs.AI 阅读全文](https://arxiv.org/abs/2611.03650)

**标签：** #arXiv

---

*AI Qazaqstan — non-commercial informational portal about AI in Kazakhstan. Machine translations and summaries are AI-generated.*