Reflect-Guard: Enhancing LLM Safeguards against Adversarial Prompts via Logical Self-Reflection 文章

ArXiv CS.AI2026-05-26NEWSen作者: Lixing Lin, Juli You, Yue Li, Luyun Lin, Yiqing Wang, Zhen Zhang, Moxuan Zheng
大语言模型
查看原文 →
关系图谱

Reflect-Guard: Enhancing LLM Safeguards against Adversarial Prompts via Logical Self-Reflection · 相关人物

暂无数据