Work

Low-Cost Document Retrieval with Dense Pseudo-Query Encoding

Year: 2025

Type: conference-paper

Abstract: Low-cost retrieval is crucial for document search on resource-limited computing platforms. This paper presents a staged sparse-to-dense retrieval framework that substitutes expensive dense query encoding with a dense pseudo-query (DPQ), an approximation derived solely from sparse retrieval results. DPQ scheme employs a simple, rank-aware weighting to combine corresponding dense representations of top sparse results, providing an opportunity to efficiently leverage an expensive but expressive LLM or BERT-based dense model without requiring GPUs. The evaluation demonstrates that DPQ-based retrieval runs fast on an affordable platform and outperforms several low-cost baselines in zero-shot retrieval.

Source: International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR)

DOI: 10.1145/3726302.3730227

Authors: Shanxiu He, Wentai Xie, Yifan Qiao, Parker Carlson, Tao Yang

Institutions: University of California, Santa Barbara, Apple (United States)

Language: English

Topic: Information Retrieval and Search Behavior

Subfield: Information Systems

Field: Computer Science

Domain: Physical Sciences

Open Access status: hybrid

Funder: National Science Foundation

Award: III: Small: Efficiency Optimization for Neural Document Ranking with Compact Representations