RECAP: Safety Alignment via Counter-Aligned Prefilling

The October 2025 academic paper introduces **RECAP (Robust Safety Alignment via Counter-Aligned Prefilling)**, a novel reinforcement learning (RL) method designed to improve the safety and robustness of large reasoning models (LRMs). The core problem addressed is the brittleness of LRMs, which are easily biased by **flawed chain-of-thought (CoT) reasoning** injected into their thought process, leading to unsafe or overly cautious responses. RECAP addresses this by explicitly training models on a mixture of standard prompts and **counter-aligned CoT prefills**—forcing the model to override unsafe reasoning for harmful queries or overly conservative refusals for benign ones to achieve a high reward. Experimental results show that RECAP substantially enhances safety, reduces overrefusal, and preserves core reasoning capabilities, leading to **more frequent self-reflection** in the models and persistent robustness against adaptive adversarial attacks. The method integrates easily with existing RL-from-human-feedback (RLHF) frameworks without incurring additional training costs.Source:https://arxiv.org/pdf/2510.00938

There are no comments yet.

Please log in to write the first comment.