English

Query Encoder Distillation via Embedding Alignment is a Strong Baseline Method to Boost Dense Retriever Online Efficiency

Information Retrieval 2023-06-21 v1 Artificial Intelligence

Abstract

The information retrieval community has made significant progress in improving the efficiency of Dual Encoder (DE) dense passage retrieval systems, making them suitable for latency-sensitive settings. However, many proposed procedures are often too complex or resource-intensive, which makes it difficult for practitioners to adopt them or identify sources of empirical gains. Therefore, in this work, we propose a trivially simple recipe to serve as a baseline method for boosting the efficiency of DE retrievers leveraging an asymmetric architecture. Our results demonstrate that even a 2-layer, BERT-based query encoder can still retain 92.5% of the full DE performance on the BEIR benchmark via unsupervised distillation and proper student initialization. We hope that our findings will encourage the community to re-evaluate the trade-offs between method complexity and performance improvements.

Keywords

Cite

@article{arxiv.2306.11550,
  title  = {Query Encoder Distillation via Embedding Alignment is a Strong Baseline Method to Boost Dense Retriever Online Efficiency},
  author = {Yuxuan Wang and Hong Lyu},
  journal= {arXiv preprint arXiv:2306.11550},
  year   = {2023}
}

Comments

Accepted by the 4th SustaiNLP workshop at ACL 2023

R2 v1 2026-06-28T11:09:41.060Z