Behavioural Analysis of Alignment Faking

Computer Science > Artificial Intelligence [Submitted on 26 May 2026] Behavioural Analysis of Alignment Faking Nathaniel Mitrani Hadida, Rhea Karty, David Williams-King, Alan Cooney Alignment faking (AF) refers to a model strategically complying with a training objective to avoid behavioural modification while preserving its deployment preferences. Understanding when and why AF arises matters as models grow better at distinguishing training from deployment. Prior work finds AF fragile, prompt-sensitive, and model-dependent, leaving its underlying drivers unclear. We study AF in a controlled, minimal setup that isolates its core components, and observe it across a wider range of models than previously reported, including small-scale models. We identify three separable drivers -- values, goal guarding, and sycophancy -- and show via targeted prompt ablations and activation steering that each independently modulates AF behaviour. Our results indicate AF is more widespread than previously reported and that its occurrence is predictable from situational cues and measurable model tendencies such as baseline sycophancy and stated values. The decomposition suggests concrete directions for detecting and mitigating AF in future models. Comments: preprint Subjects: Artificial Intelligence (cs.AI); Machine Learning (cs.LG) ACM classes: I.2.7 Cite as: arXiv:2605.27681 [cs.AI]   (or arXiv:2605.27681v1 [cs.AI] for this version)   https://doi.org/10.48550/arXiv.2605.27681 Focus to learn more Submission history From: David Williams-King [view email] [v1] Tue, 26 May 2026 21:00:35 UTC (2,793 KB) Access Paper: HTML (experimental) view license Current browse context: cs.AI < prev   |   next > new | recent | 2026-05 Change to browse by: cs cs.LG References & Citations NASA ADS Google Scholar Semantic Scholar Export BibTeX Citation Bookmark Bibliographic Tools Bibliographic and Citation Tools Bibliographic Explorer Toggle Bibliographic Explorer (What is the Explorer?) Connected Papers Toggle Connected Papers (What is Connected Papers?) Litmaps Toggle Litmaps (What is Litmaps?) scite.ai Toggle scite Smart Citations (What are Smart Citations?) Code, Data, Media Demos Related Papers About arXivLabs Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)