$\mathrm{R}\mathrm{EAL}\mathrm{G}\mathrm{UARD}$: Reliable, Efficient, and Auditable LLM Safeguards via Latent Reasoning

Zhinan Liu, Jie Li, Mingyu Kang +1

Reasoning-based large language model (LLM) safeguards improve safety classification accuracy by generating explicit rationales before making decisions. However, generating explicit…