Zero-Shot Multilingual Retrieval Performance of Hybrid Batch Versus Contrastive Learning Strategies on the XBEIR 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: How does the zero-shot retrieval performance (measured by nDCG@10) of multilingual models trained with the hybrid batch strategy compare to contrastive learning strategies on the XBEIR benchmark when evaluated across 10+ languages?

Autonomous synthesis report generated by Assignee Research. Tribunal consensus score: 7.7/10.