2026
Efficient Switchable Safety Control in LLMs via Magic-Token-Guided Co-Training
AAAI 2026technical
Current methods for content safety in Large Language Models (LLMs), such as Supervised Fine-Tuning (SFT) and Reinforcement Learning from Human Feedback (RLHF), often rely on multi-stage training pipelines and lack fine-grained, post-deployment controllability. To address these limitations, we propos