Cross-lingual retrieval-augmented generation (RAG) is a critical capability for retrieving and generating answers across languages. Prior work in this context has mostly focused on generation and relied on benchmarks derived from open-domain sources, most notably Wikipedia. In such settings, retrieval challenges often remain hidden due to language imbalances, overlap with pretraining data, and memorized content. To address this gap, we study Arabic-English RAG in a domain-specific setting using benchmarks derived from real-world corporate datasets. Our benchmarks include all combinations of languages for the user query and the supporting document, drawn independently and uniformly at random. This enables a systematic study of multilingual retrieval behavior. Our findings reveal that retrieval is a critical bottleneck in cross-lingual domain-specific scenarios, with substantial performance drops occurring when the user query and supporting document languages differ. A key insight is that these failures stem primarily from the retriever's difficulty in ranking documents across languages. Finally, we propose two simple retrieval strategies that address this source of failure by enforcing equal retrieval from both languages or by translating the query, resulting in substantial improvements in cross-lingual and overall performance. These results highlight meaningful opportunities for improving multilingual retrieval, particularly in practical, real-world RAG applications.

翻译：跨语言检索增强生成（RAG）是实现跨语言检索与答案生成的关键能力。现有研究主要聚焦于生成环节，并依赖基于开放域数据源（尤其是维基百科）构建的基准测试集。在此类设定中，由于语言不平衡、与预训练数据的重叠以及记忆化内容等因素，检索环节的挑战往往被掩盖。为弥补这一研究空白，我们基于真实企业数据集构建的领域专用基准测试，对阿拉伯语-英语跨语言RAG展开研究。我们的基准测试涵盖用户查询与支持文档的所有语言组合，且均通过独立均匀随机抽样获取，从而实现对多语言检索行为的系统性研究。研究发现：在跨语言领域专用场景中，检索环节构成关键瓶颈——当用户查询与支持文档语言不一致时，系统性能出现显著下降。核心机制分析表明，这些失败主要源于检索器在跨语言文档排序中遇到的困难。最后，我们提出两种简易检索策略：通过强制均衡双语检索或实施查询翻译来应对这一失效根源。实验表明，这两种策略显著提升了跨语言场景及整体性能。这些发现为改进多语言检索系统（特别是在实际应用场景中的RAG系统）揭示了具有实践价值的研究方向。