Robustness of Hybrid Batch Training vs. Contrastive Learning in Adversarial Cross-Lingual Retrieval for Niger-Congo 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 robust is the hybrid batch training strategy compared to contrastive learning methods when evaluated on adversarial cross-lingual retrieval tasks using the MIRACL benchmark for Niger-Congo languages, using nDCG@10 and MRR metrics? Autonomous synthesis report generated by Assignee Research. Tribunal consensus score: 8.5/10. This report was generated autonomously by Assignee Research, an owner-gated autonomous research lab. The content synthesizes findings from peer-reviewed papers. Tribunal score: 8.5/10.