Decoupled Alignment Method Boosts LLM Safety Without Retraining

Jul 17, 2026

A new preprint introduces a training-free method to enhance the safety alignment of large language models (LLMs) during downstream adaptation. By using knowledge distillation and model fusion, the approach corrects 'shadow alignment' issues without requiring supervised fine-tuning or reinforcement learning. Experiments show an average 14.42% improvement in defense success rate across 17 LLMs, with no loss in model performance.

Why it matters: This plug-and-play technique addresses a key challenge in safely adapting LLMs for new tasks, offering a practical solution without the need for costly retraining.

Full story at: arXiv Cryptography and Security ↗