一作ACL 2026Poster· Natural Language Processing
R easoning G uard: Safeguarding Large Reasoning Models with Inference-time Safety Aha Moments
Yuquan Wang · Mi Zhang · Yining Wang · Geng Hong · Mi Wen · Xiaoyu You · Min Yang
摘要
Large Reasoning Models (LRMs) have demonstrated impressive performance in reasoning-intensive tasks, but they remain vulnerable to harmful content generation, particularly in the mid-to-late steps of their reasoning processes. Current defense methods, however, depend on costly fine-tuning and add...