Journal Article

Reasoning over Public and Private Data in Retrieval-Based Systems

Arora, Simran, Fan, Angela, Lewis, Patrick, Kahn, Jacob, Ré, Christopher

2023

Overview

Users an organizations are generating ever-increasing amounts of private data from a wide range of sources. Incorporating private context is important to personalize open-domain tasks such as question-answering, fact-checking, and personal assistants. State-of-the-art systems for these tasks explicitly retrieve information that is relevant to an input question from a background corpus before producing an answer. While today’s retrieval systems assume relevant corpora are fully (e.g., publicly) accessible, users are often unable or unwilling to expose their private data to entities hosting public data. We define the ( ) problem involving iterative retrieval over multiple privacy scopes. We introduce a foundational benchmark with which to study , as no existing benchmark includes data from a private distribution. Our dataset, , includes data from distinct public and private distributions and is the first textual QA benchmark requiring concurrent retrieval over multiple distributions. Finally, we show that existing retrieval approaches face significant performance degradations when applied to our proposed retrieval setting and investigate approaches with which these tradeoffs can be mitigated. We release the new benchmark and code to reproduce the results.

• Publisher: MIT Press,MIT Press Journals, The,The MIT Press
• Subject: Benchmarks / Computational linguistics / Computerized corpora / Data / Grammatical aspect / Information retrieval / Performance degradation / Personal assistants / Privacy / Questions / Retrieval