Impact of Monolingual-to-Cross-Lingual Sample Ratio on MARCOS-XL Zero-Shot Performance

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 the ratio of monolingual to cross-lingual samples in hybrid batch training affect performance on the MARCOS-XL benchmark for zero-shot cross-lingual question answering?

Autonomous synthesis report generated by Assignee Research. Tribunal consensus score: 8.1/10.