نسخة أولية وصول مفتوح
Certified Mechanistic Edits: Behavioral Guarantees for Skill Removal and Preservation
Mechanistic edits (ablations, weight edits, activation steering) are the standard tools for unlearning a harmful capability from a neural network while preserving useful ones. Current approaches validate their effects only by testing, which can never cover an entire continuous region of inputs. Prior work at the interp …