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

> Полный текст доступен на английском

**Published:** 4 ноября 2026 г.
**Author:** Manodeep Ray, Vivek Srivastava, Shirish Karande, Murari Mandal
**Source:** arXiv — cs.AI
**Language:** en-US
**HTML:** https://aiqazaqstan.com/ru/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…

> Материал агрегирован из первоисточника: **arXiv — cs.AI**
> [Читать полностью в arXiv — cs.AI](https://arxiv.org/abs/2611.03650)

**Теги:** #arXiv

---

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