Boosting Data Utilization for Multilingual Dense Retrieval
Chao Huang, Fengran Mo, Yufeng Chen, Changhao Guan, Zhenrui Yue, Xinyu Wang, Jinan Xu, Kaiyu Huang
Abstract
Multilingual dense retrieval aims to retrieve relevant documents across different languages based on a unified retriever model. The challenge lies in aligning representations of different languages in a shared vector space. The common practice is to fine-tune the dense retriever via contrastive learning, whose effectiveness highly relies on the quality of the negative sample and the efficacy of mini-batch data. Different from the existing studies that focus on developing sophisticated model architecture, we propose a method to boost data utilization for multilingual dense retrieval by obtaining high-quality hard negative samples and effective mini-batch data. The extensive experimental results on a multilingual retrieval benchmark, MIRACL, with 16 languages demonstrate the effectiveness of our method by outperforming several existing strong baselines.
BibTeX
@inproceedings{emnlp2025_boostingdatautil,
title = {Boosting Data Utilization for Multilingual Dense Retrieval},
author = {Chao Huang and Fengran Mo and Yufeng Chen and Changhao Guan and Zhenrui Yue and Xinyu Wang and Jinan Xu and Kaiyu Huang},
booktitle = {EMNLP 2025},
year = {2025}
}