RAG with Differential Privacy

TL;DR

This paper proposes a differentially private token generation method for Retrieval-Augmented Generation (RAG) to ensure privacy when integrating external documents, addressing confidentiality concerns in large language models.

Contribution

It introduces a practical differentially private approach to RAG, enabling secure knowledge extraction from sensitive data without compromising privacy.

Findings

Differentially private token generation is feasible for RAG.

The approach mitigates privacy risks in knowledge retrieval.

Enhanced privacy guarantees in large language model applications.

Abstract

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.