用私有生成文本替代敏感数据，实现可复用的隐私保护检索增强生成。
Differentially Private Synthetic Text Generation for Retrieval-Augmented Generation (RAG)
- 利用大模型生成符合差分隐私的合成文本数据库，避免重复加噪。
- 在固定隐私预算下性能优于现有最先进方法，支持长期复用。
- 适合医疗、金融等需高隐私保护的领域应用。
检索增强生成（RAG）通过引入外部知识提升大语言模型性能，但在敏感领域因隐私风险受限。现有私有RAG方法多依赖查询时差分隐私（DP），需反复注入噪声，导致隐私损耗累积。为此，本文提出DP-SynRAG框架，利用大模型生成差分隐私的合成RAG数据库。与以往方法不同，生成的合成文本可一次性创建并重复使用，避免多次加噪和额外隐私成本。为保留下游RAG任务所需信息，DP-SynRAG扩展了私有预测机制，指导大模型以差分隐私方式生成模仿子采样数据库记录的文本。实验表明，DP-SynRAG在固定隐私预算下性能显著优于当前最先进的私有RAG系统，提供了一种可扩展的隐私保护RAG解决方案。
原文摘要 · Abstract (English)
Retrieval-Augmented Generation (RAG) enhances large language models (LLMs) by grounding them in external knowledge. However, its application in sensitive domains is limited by privacy risks. Existing private RAG methods typically rely on query-time differential privacy (DP), which requires repeated noise injection and leads to accumulated privacy loss. To address this issue, we propose DP-SynRAG, a framework that uses LLMs to generate differentially private synthetic RAG databases. Unlike prior methods, the synthetic text can be reused once created, thereby avoiding repeated noise injection and additional privacy costs. To preserve essential information for downstream RAG tasks, DP-SynRAG extends private prediction, which instructs LLMs to generate text that mimics subsampled database records in a DP manner. Experiments show that DP-SynRAG achieves superior performance to the state-of-the-art private RAG systems while maintaining a fixed privacy budget, offering a scalable solution for 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。