PILLAR：用于增强检索的私有倒排索引词法查找

中文摘要 AI 辅助

检索增强生成（RAG）将用户的查询交给托管语料库的服务器。我们提出PILLAR，一种基于私有信息检索（PIR）的隐私保护RAG（PPRAG）系统，其中客户端利用服务器持有且公开已知的语料库中与查询最相似的k个文档来响应查询，而服务器对查询一无所知，无论是其词项还是访问模式。先前的PPRAG构造仅依赖密集检索，将近似最近邻搜索转化为许多依赖查询的PIR轮次，并在延迟和检索质量上付出代价。PILLAR则分两个阶段进行私有混合检索。稀疏阶段针对精心设计的预计算BM25分数索引发出少量固定数量的PIR查询，将语料库过滤为与查询共享词项的候选集，而服务器永远看不到这些词项。密集阶段仅获取这些候选的文档嵌入并在本地重新排序，避免了私有密集检索通常需要的许多昂贵PIR查询。我们使用两种协议实例化PILLAR，它们在延迟和检索质量之间权衡，每种协议基于不同的私有词法搜索渲染。PILLAR-Bin将发布列表分箱到哈希表中，是一种单轮设计，比最先进的私有检索方案实现更低的延迟。PILLAR-Tree将块最大剪枝转化为结合布谷鸟哈希表的遗忘树遍历，并以比最先进方案更低的延迟实现最高的检索质量。

英文摘要

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.

发表机构

• Arizona State University（亚利桑那州立大学）
• George Mason University（乔治梅森大学）

机构由 AI 辅助整理，请以论文原文为准。