用差分隐私保护私有数据的RAG生成，防止信息泄露。
RAG with Differential Privacy
- 在RAG中引入差分隐私机制，确保生成内容不泄露敏感信息。
- 证明差分隐私令牌生成可有效实现私有知识提取。
- 适合关注隐私保护的个人数据应用场景。
检索增强生成（RAG）已成为主流技术，使大型语言模型（LLM）能够获取最新且相关的上下文，从而降低幻觉风险并提升响应质量，尤其适用于大规模、快速更新的知识库环境。然而，将外部文档融入生成过程会引发显著的隐私问题：即使将文档加入提示词，也无法保证响应不会意外暴露机密数据，可能导致隐私泄露和伦理困境。本文探索了一种适用于从个人数据中提取通用知识的实用解决方案，表明差分隐私令牌生成是实现私有RAG的可行方法。
原文摘要 · Abstract (English)
Retrieval-Augmented Generation (RAG) has emerged as the dominant technique to provide \emph{Large Language Models} (LLM) with fresh and relevant context, mitigating the risk of hallucinations and improving the overall quality of responses in environments with large and fast moving knowledge bases. However, the integration of external documents into the generation process raises significant privacy concerns. Indeed, when added to a prompt, it is not possible to guarantee a response will not inadvertently expose confidential data, leading to potential breaches of privacy and ethical dilemmas. This paper explores a practical solution to this problem suitable to general knowledge extraction from personal data. It shows \emph{differentially private token generation} is a viable approach to private 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。