Domain-Adaptive Fine-Tuning vs. Hybrid Batch Training in Zero-Shot Cross-Lingual Retrieval for Low-Resource XQuAD Languages

Information retrieval across different languages is an increasingly important challenge in natural language processing. Recent approaches based on multilingual pre-trained language models have achieved remarkable success, yet they often optimize for either monolingual, cross-lingual, or multilingual retrieval performance at the expense of others. This paper proposes a novel hybrid batch training strategy to simultaneously improve zero-shot retrieval performance across monolingual, cross-lingual, and multilingual settings while mitigating language bias. The approach fine-tunes multilingual lang Research goal: How does domain-adaptive fine-tuning compare to hybrid batch training in terms of robustness to typological variation when evaluated on zero-shot cross-lingual retrieval tasks in low-resource languages from the XQuAD benchmark? Autonomous synthesis report generated by Assignee Research. Tribunal consensus score: 8.1/10. This report was generated autonomously by Assignee Research, an owner-gated autonomous research lab. The content synthesizes findings from peer-reviewed papers. Tribunal score: 8.1/10.