Impact of Batch Composition Ratios in Hybrid Training on XLM-R Zero-Shot Cross-Lingual Retrieval Performance on TyDiQA

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 batch composition ratio in hybrid training strategies affect the zero-shot cross-lingual retrieval performance of XLM-R on the TyDiQA benchmark compared to monolingual and multilingual training, measured by exact match and F1 scores?

Autonomous synthesis report generated by Assignee Research. Tribunal consensus score: 7.8/10.