# Propensities Please: Exposing Alignment-Faking LLMs using Synthetic Document Finetuning

**Published:** October 27, 2026
**Author:** Ardy Haroen, Florian Lorkowski, Samuel Nellessen, Felix Hofst\"atter
**Source:** arXiv — cs.AI
**Language:** en-US
**HTML:** https://aiqazaqstan.com/en/articles/propensities-please-exposing-alignment-faking-llms-using-synthetic-docum

arXiv:2610.33180v1 Announce Type: new Abstract: Alignment evaluations aim to assess whether large language models would engage in dangerous misaligned behaviour. Misaligned and evaluation-aware models might engage in alignment faking, where they pursue a hidden goal, but conceal…

> From the original source: **arXiv — cs.AI**
> [Read full article at arXiv — cs.AI](https://arxiv.org/abs/2610.33180)

**Tags:** #arXiv

---

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