One-Shot Safety Alignment for Large Language Models via Optimal Dualization

The growing safety concerns surrounding LLMs raise an urgent need to align them with diverse human preferences to simultaneously enhance their helpfulness and safety. A promising approach is to enforce safety constraints through Reinforcement Learning from Human Feedback (RLHF). For such constrained RLHF, common Lagrangian-based primal-dual policy optimization methods are computationally expensive and often unstable. This paper presents a dualization perspective that reduces constrained alignment to an equivalent unconstrained alignment problem. We do so by pre-optimizing a smooth and convex dual function that has a closed form. This shortcut eliminates the need for cumbersome primal-dual policy iterations, thus greatly reducing the computational burden and improving training stability. Our strategy leads to two practical algorithms in model-based and preference-based scenarios (MoCAN and PeCAN, respectively). A broad range of experiments demonstrate the effectiveness of our methods.