Impact of Hybrid Batch Training Ratios on Zero-Shot Retrieval Performance in Multilingual Language Models

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 hybrid batch training ratio of monolingual, cross-lingual, and multilingual samples impact the zero-shot retrieval performance (MRR) of multilingual language models on low-resource languages in the BEIR benchmark compared to high-resource languages?

Autonomous synthesis report generated by Assignee Research. Tribunal consensus score: 7.5/10.