Behavioural Analysis of Alignment Faking
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 rang
Record details
Published: 26 May 2026
Source: arXiv
Category: Research
Topics: Safety & alignment
Retrieved: 14 July 2026
Related evidence
These records share source-supplied organisations, an exact publisher byline, automatic topics or regions. The reason is shown on every link; related does not mean supporting, agreeing with or verifying this record.
DeepSciVerify: Verifying Scientific Claim--Citation Alignment via LLM-Driven Evidence Escalation
arXiv · 26 May 2026
Latent Goal Prediction from Language for Model-Based Planning
arXiv · 26 May 2026
Intelligence as Managed Autonomy: Failure, Escalation, and Governance for Agentic AI Systems
arXiv · 26 May 2026
Alignment Tampering: How Reinforcement Learning from Human Feedback Is Exploited to Optimize Misaligned Biases
arXiv · 26 May 2026
When Eyes Betray AI: Social Gaze Consistency as a Semantic Cue for AI-Generated Image Detection
arXiv · 26 May 2026
Falcon-X: A Time Series Foundation Model for Heterogeneous Multivariate Modeling
arXiv · 26 May 2026
How to cite this record
ethics.ai (26 May 2026), “Behavioural Analysis of Alignment Faking,” evidence record 3644, https://ethics.ai/record/3644 (originally published by arXiv).
Use and limitations
This page is a stable index and citation surface for a source record. ethics.ai did not author the underlying report and has not independently verified every claim. Automatic topics may be imperfect. For consequential use, quote and cite the original publisher.