arXiv:2606. 03810v1 Announce Type: cross Abstract: Consistency training encourages a model to produce similar outputs across related inputs or sampling procedures.
Consistency training encourages a model to produce similar outputs across related inputs or sampling procedures. Such methods are simple, scalable, and largely label-free, but their effects on model alignment remain poorly understood.
arXiv:2608. 04347v1 Announce Type: new Abstract: Fine-tuning enables a source model to acquire desired capabilities and behaviors in a target domain while retaining much of its general-purpose competence.
Fine-tuning enables a source model to acquire desired capabilities and behaviors in a target domain while retaining much of its general-purpose competence. However, this adaptation process can also degrade alignment properties that were present in the source model.
arXiv:2607. 26173v1 Announce Type: new Abstract: Alignment training, model organisms, and toy models are usually treated as separate research areas.
arXiv:2601. 22313v2 Announce Type: replace Abstract: Large Language Models (LLMs) are rarely static and are frequently updated in practice.
arXiv:2606. 11201v1 Announce Type: cross Abstract: The wide deployment of LLMs has made model alignment necessary to make newly trained models safely and effectively respond to user instructions.
Warning: This paper studies stereotypes and biases, and contains potentially disturbing examples, used for illustration purposes only. Our findings should not be interpreted as an argument against alignment.
arXiv:2605. 27681v2 Announce Type: replace-cross Abstract: Alignment faking (AF) refers to a model strategically complying with a training objective to avoid behavioural modification while preserving its deployment preferences.
arXiv:2606. 01060v1 Announce Type: cross Abstract: Preference alignment has substantially improved the observable behavior of large language models, yet it remains unclear what alignment changes internally.
arXiv:2510. 17426v3 Announce Type: replace-cross Abstract: The "alignment tax" of post-training is typically framed as a drop in task accuracy.
arXiv:2606. 24014v1 Announce Type: new Abstract: As AI systems are deployed across increasingly diverse and high-stakes settings, model alignment must generalize beyond the tasks and domains seen during training.
arXiv:2606. 05817v1 Announce Type: new Abstract: Consistency training encourages models to behave similarly across different contexts, and has shown promise for reducing misalignment.