Robustness Comparison of Zero-Shot Cross-Lingual Retrieval in Hybrid Batch Training and Monolingual Fine-Tuning on XCOP Benchmark

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: What are the robustness differences in zero-shot cross-lingual retrieval performance between the hybrid batch training approach and monolingual fine-tuning when evaluating on adversarial or low-resource language pairs in the XCOP benchmark? Autonomous synthesis report generated by Assignee Research. Tribunal consensus score: 8.3/10. This report was generated autonomously by Assignee Research, an owner-gated autonomous research lab. The content synthesizes findings from peer-reviewed papers. Tribunal score: 8.3/10.