# Augmenting Passage Representations with Query Generation for Enhanced Cross-Lingual Dense Retrieval

arXiv: https://arxiv.org/abs/2305.03950 · HTML: https://mlsanity.com/paper/2305.03950/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 6 May 2023.

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

- [Leveraging LLMs for Synthesizing Training Data Across Many Languages in Multilingual Dense Retrieval](https://mlsanity.com/paper/2311.05800/) (2023)
- [Preserving Multilingual Quality While Tuning Query Encoder on English Only](https://mlsanity.com/paper/2407.00923/) (2024)
- [CLEAR: Cross-Lingual Enhancement in Alignment via Reverse-training](https://mlsanity.com/paper/2604.05821/) (2026)
- [Large Language Models for Stemming: Promises, Pitfalls and Failures](https://mlsanity.com/paper/2402.11757/) (2024)
- [Test-Time Training for Zero-Resource Dense Retrieval Reranking](https://mlsanity.com/paper/2606.01070/) (2026)

## Abstract (arXiv)

Effective cross-lingual dense retrieval methods that rely on multilingual pre-trained language models (PLMs) need to be trained to encompass both the relevance matching task and the cross-language alignment task. However, cross-lingual data for training is often scarcely available. In this paper, rather than using more cross-lingual data for training, we propose to use cross-lingual query generation to augment passage representations with queries in languages other than the original passage language. These augmented representations are used at inference time so that the representation can encode more information across the different target languages. Training of a cross-lingual query generator does not require additional training data to that used for the dense retriever. The query generator training is also effective because the pre-training task for the generator (T5 text-to-text training) is very similar to the fine-tuning task (generation of a query). The use of the generator does not increase query latency at inference and can be combined with any cross-lingual dense retrieval method. Results from experiments on a benchmark cross-lingual information retrieval dataset show that our approach can improve the effectiveness of existing cross-lingual dense retrieval methods. Implementation of our methods, along with all generated query files are made publicly available at https://github.com/ielab/xQG4xDR.