Extracting Persona Subspaces Through Iterative Nullspace Projection For Modulation
Large Language Models (LLMs) can adopt distinct personas to tune their semantics, expertise, and perspective to different users and tasks. Precise control over these traits is critical to ensure safety and reliability in model behavior. Existing methods like activation steering and prompt-based persona induction reduce a persona to a single dominant direction, missing the finer, nested traits…
We haven't written up this one. arXiv cs.AI has the full story — the link below goes straight to it.