Yanxu Mao

You Are an Expert: RAG Injection and Guided Error Expert Activation for Jailbreaking Large Language Models

This work proposes a novel jailbreak framework: YAE, which enhances the model's dependency on external information by constructing a RAG‐based knowledge base containing harmful Q&A content and leverages Guide MoE, a routing‐inspired prompting strategy, to guide the model toward alternative reasoning trajectories through expert‐role prompting and domain‐specific perturbations.