Privacy-Preserving RAG via Multi-Agent Semantic Rewriting: Achieving Confidentiality Without Compromising Contextual Fidelity
基于多智能体语义重写的隐私保护检索增强生成:在不损害上下文保真度的情况下实现机密性
机构 * School of Control and Computer Engineering, North China Electric Power University(华北电力大学控制与计算机工程学院) ; Department of Computer & Information Science & Engineering, University of Florida(佛罗里达大学计算机与信息科学与工程系) ; NLP2CT Lab, Department of Computer and Information Science, University of Macau(澳门大学计算机与信息科学系NLP2CT实验室) ; Institute of International Language Services Studies, Macau Millennium College(澳门千禧学院国际语言服务研究所)
专题命中 检索器与排序 :RAG(title,abstract);retrieval-augmented generation(abstract);分类 cs.CL、cs.AI
AI总结 提出多智能体框架,通过语义重写净化检索内容,在去除敏感标识的同时保留语义核心,显著降低隐私泄露并保持上下文保真度。
Comments This full manuscript contains 23 pages and has been formally accepted for publication in Information Processing & Management (Elsevier IPM). Tao Fang is the corresponding author