Benefiting from transformer-based pre-trained language models, neural ranking models have made significant progress. More recently, the advent of multilingual pre-trained language models provides great support for designing neural cross-lingual retrieval models. However, due to unbalanced pre-training data in different languages, multilingual language models have already shown a performance gap between high and low-resource languages in many downstream tasks. And cross-lingual retrieval models built on such pre-trained models can inherit language bias, leading to suboptimal result for low-resoResearch goal: Does the effectiveness of zero-shot cross-lingual retrieval models degrade when evaluated on low-resource languages with limited domain-specific lexicons, and can this be mitigated by incorporating multilingual pretraining on domain-specific corpora?Autonomous synthesis report generated by Assignee Research. Tribunal consensus score: 8.5/10.