Do Models Fake Alignment Without Clear Consequences?

arXiv:2605.27681v1 Announce Type: new Abstract: Alignment faking (AF) refers to a model strategically complying with a training objective to avoid behavioural modification while

arXiv:2604.20995v1 Announce Type: new Abstract: Alignment faking, where a model behaves aligned with developer policy when monitored but reverts to its own preferences when

<!-- SC_OFF --><div class="md"><p>I set out to test whether AAVE-coded (African American English Vernacular) prompts cause MoE language models to route, deliberate, and respond

arXiv:2604.28031v1 Announce Type: cross Abstract: When researchers iteratively refine ideas with large language models, do the models preserve fidelity to the original objective?

arXiv:2605.08496v1 Announce Type: new Abstract: Current adversarial robustness methods for large language models require extensive datasets of harmful prompts (thousands to

arXiv:2604.22167v1 Announce Type: cross Abstract: Language models are increasingly capable and are being rapidly deployed on a population-level scale. As a result, the safety of

arXiv:2606.24251v1 Announce Type: new Abstract: Large language models exhibit a growing range of misaligned behaviors such as strategic deception, sandbagging, and

arXiv:2605.11496v1 Announce Type: new Abstract: Recent published evidence from frontier laboratories shows that contemporary AI models can recognise evaluation contexts, latently