# Empowering Dual-Encoder with Query Generator for Cross-Lingual Dense Retrieval

arXiv: https://arxiv.org/abs/2303.14991 · HTML: https://mlsanity.com/paper/2303.14991/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 27 Mar 2023.

## Built on by (most cited first, 5 of 5)

- [Alignment with Fill-In-the-Middle for Enhancing Code Generation](https://mlsanity.com/paper/2508.19532/) (2025)
- [Pre-training Cross-lingual Open Domain Question Answering with Large-scale Synthetic Supervision](https://mlsanity.com/paper/2402.16508/) (2024)
- [Unsupervised Multilingual Dense Retrieval via Generative Pseudo Labeling](https://mlsanity.com/paper/2403.03516/) (2024)
- [Preserving Multilingual Quality While Tuning Query Encoder on English Only](https://mlsanity.com/paper/2407.00923/) (2024)
- [Few-Shot Multilingual Open-Domain QA from 5 Examples](https://mlsanity.com/paper/2502.19722/) (2025)

## Abstract (arXiv)

In monolingual dense retrieval, lots of works focus on how to distill knowledge from cross-encoder re-ranker to dual-encoder retriever and these methods achieve better performance due to the effectiveness of cross-encoder re-ranker. However, we find that the performance of the cross-encoder re-ranker is heavily influenced by the number of training samples and the quality of negative samples, which is hard to obtain in the cross-lingual setting. In this paper, we propose to use a query generator as the teacher in the cross-lingual setting, which is less dependent on enough training samples and high-quality negative samples. In addition to traditional knowledge distillation, we further propose a novel enhancement method, which uses the query generator to help the dual-encoder align queries from different languages, but does not need any additional parallel sentences. The experimental results show that our method outperforms the state-of-the-art methods on two benchmark datasets.