Don't Forget Private Retrieval: Distributed Private Similarity Search For Large Language Models

Abstract

While the flexible capabilities of large language models (LLMs) allow them to answer a range of queries based on existing learned knowledge, information retrieval to augment generation is an important tool to allow LLMs to answer questions on information not included in pre-training data. Such private information is increasingly being generated in a wide array of distributed contexts by organizations and individuals. Performing such information retrieval using neural embeddings of queries and documents always leaked information about queries and database content unless both were stored locally. We present Private Retrieval Augmented Generation (PRAG), an approach that uses multi-party computation (MPC) to securely transmit queries to a distributed set of servers containing a privately constructed database to return top-k and approximate top-k documents. This is a first-of-its-kind approach to dense information retrieval that ensures no server observes a client's query or can see the da

Stats

• citations4
• S2 citations—
• github stars0
• HF likes0
• heat score5.24
• arxiv keyzyskind2023don

Related papers

• Improving Tool Retrieval By Leveraging Large Language Models For Query Generation (2024)0.00
• Synthetic Query Generation For Privacy-preserving Deep Retrieval Systems Using Differentially Private Language Models (2023)4.52
• Pseudo Relevance Feedback Is Enough To Close The Gap Between Small And Large Dense Retrieval Models (2025)0.00
• Scalingnote: Scaling Up Retrievers With Large Language Models For Real-world Dense Retrieval (2024)0.00
• Large Language Models Are Built-in Autoregressive Search Engines (2023)13.49
• SLQ: Bridging Modalities Via Shared Latent Queries For Retrieval With Frozen Mllms (2026)0.00
• Expandr: Teaching Dense Retrievers Beyond Queries With LLM Guidance (2025)3.25
• Making Large Language Models Efficient Dense Retrievers (2025)0.00