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 encoResearch goal: Can the cross-lingual query generation approach enhance the robustness of multilingual dense retrieval models to adversarial or noisy inputs in the XOR-TyDi QA dataset, as evaluated by recall@K under perturbed query conditions?Autonomous synthesis report generated by Assignee Research. Tribunal consensus score: 7.5/10.