用多智能体重写检索内容，保护隐私同时不丢语义。
Privacy-Preserving RAG via Multi-Agent Semantic Rewriting: Achieving Confidentiality Without Compromising Contextual Fidelity
- 三智能体协作：提取隐私、分析语义、重建文本
- 攻击下隐私泄露从144降至1，BLEU-1达0.122
- 离线处理零延迟，适合医疗等高敏感场景
检索增强生成通过引入外部知识提升大模型性能，但在敏感场景中可能因恶意提示导致隐私泄露。为此，我们提出一种多智能体框架，通过语义重写对检索内容进行净化。该框架包含三个专用智能体：隐私提取、语义分析与内容重建，协同移除敏感标识符同时保留语义核心。我们在ChatDoctor和Wiki-PII数据集上，针对六种大语言模型进行评估。实验表明，在定向攻击下隐私泄露显著降低：例如，LLaMA-3-8B的敏感信息暴露从基线的144例降至1例。同时，上下文保真度保持良好，BLEU-1得分为0.122，优于现有SAGE方法的0.117。此外，该框架作为异步预处理模块运行，所有重写操作均为离线一次性完成，不影响在线推理延迟。为促进可复现性，代码已公开于https://github.com/foursoils/Privacy-Preserving-RAG。
原文摘要 · Abstract (English)
Retrieval-Augmented Generation enhances large language models by incorporating external knowledge, but deploying it in sensitive scenarios risks privacy leakage via malicious prompts. To address this, we propose a multi-agent framework that sanitizes retrieved content through semantic rewriting. By employing three specialized agents for privacy extraction, semantic analysis, and reconstruction, our approach collaboratively removes sensitive identifiers while preserving the semantic core. We evaluate the framework on the ChatDoctor and Wiki-PII datasets across six large language models. Experimental results demonstrate a significant reduction in privacy leakage under targeted attacks. For instance, we reduced targeted information exposure in LLaMA-3-8B from 144 instances in the baseline to just 1. Furthermore, we maintain strong contextual fidelity with a BLEU-1 score of 0.122, outperforming the existing SAGE method's 0.117. Finally, the framework operates as an asynchronous preprocessing module, introducing no additional latency to online inference, as all rewriting is executed as a one-time offline preprocessing step. To promote reproducibility, the source code of this work is publicly available at https://github.com/foursoils/Privacy-Preserving-RAG.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。