Back to papers
August 31, 2026cs.LGcs.CL
Controlling Refusal Behavior of LLMs via Stiefel-Constrained Rotation Steering
Kirill Bunin, Dmitry Bylinkin, Vladimir Aletov, Daniil Medyakov, Vladimir Solodkin, Aleksandr Beznosikov
Categories
cs.LG, cs.CL
cs.LG, cs.CL