Skip to content

PILLAR: Private Inverted-Index Lexical Lookup for Augmented Retrieval

Sep 2026 · 0 citations · 42 references
Computer Science

TL;DR

PILLAR is a Privacy-Preserving RAG system based on Private Information Retrieval (PIR) in which a client utilizes the k documents most similar to their query from a server-held and publicly known corpus to respond to their query, while the server learns nothing about the query, either its terms or its access pattern.

Abstract

Retrieval-augmented generation (RAG) hands the user's query to whoever hosts the corpus. We propose PILLAR, a Privacy-Preserving RAG (PPRAG) system based on Private Information Retrieval (PIR) in which a client utilizes the k documents most similar to their query from a server-held and publicly known corpus to respond to their query, while the server learns nothing about the query, either its terms or its access pattern. Prior PPRAG constructions rely on dense retrieval alone, translating approximate nearest-neighbor search into many query-dependent rounds of PIR, and pay for it in both latency and retrieval quality. PILLAR instead performs private hybrid retrieval in two stages. A sparse stage issues a small, fixed number of PIR queries against a carefully designed index of precomputed BM25 scores, filtering the corpus down to candidates that share terms with the query without the server ever seeing which terms these are. A dense stage then fetches only those candidates'document embeddings and re-ranks them locally, avoiding the many costly PIR queries that private dense retrieval typically requires. We instantiate PILLAR with two protocols that trade latency against retrieval quality, each built on a different private rendering of lexical search. PILLAR-Bin bins posting lists into a hash table and is a single-round design that achieves lower latency than state-of-the-art private retrieval schemes. PILLAR-Tree turns block-max pruning into an oblivious tree traversal combined with cuckoo hash tables and achieves the highest retrieval quality at lower latency than state-of-the-art schemes.

View source

Similar papers

#artificial intelligence Preprint Sep 2026

Shadow Queries for Private Retrieval in Vector Databases

SHAQ (shadow query generation), a semantic-decomposition and embedding-decoupling defense against EIAs, is proposed, which uses a generative language model to create diverse shadow queries that capture different semantic aspects of each document.

Xinguo Feng, Zhongkui Ma, Zi-Han Wang et al. · 0 citations
#machine learning Preprint Sep 2026

Spruce: Scalable Private Outsourced Retrieval Using Compact Embeddings

Spruce learns compact binary codes that preserve candidates for full-precision reranking, replacing corpus-wide embedding scoring with efficient Hamming-distance computation under two-server multi-party computation under two-server multi-party computation (MPC).

Pei-Chun Hua, Yun-Ming Xiao · 4 citations
#natural language process... Preprint Oct 2026

Finding the Right Balance: Relevance and Diversity in LLM Retrieval

It is concluded that diversification should be used selectively, based on observable redundancy and evidence requirements, and introduces a query-adaptive rule that diversifies only when the effective number of distinct documents in the nearest-neighbor top-$k$ selection falls below the query's evidence requirement.

Guillaume Brouillette, Faustin Kagabo, Usef Faghihi et al. · 0 citations
#artificial intelligence Open access Sep 2026

ORDER: Task-Conditioned Routing for Retrieval-Augmented Generation

Retrieval-Augmented Generation (RAG) pipelines typically rely on a fixed indexing and retrieval configuration determined at preprocessing time. This one-size-fits-all design is ill-suited to domain-expert settings, where heterogeneous queries require different chunking granularities, metadata constraints, and source-se...

Aurélien Pellet, Marie Puren, Julien Perez · 0 citations

Related blog posts

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.