Hybrid Batch Training for Cross-Lingual Retrieval on BEIR Across 10B to 50B Parameter 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: Can the hybrid batch training strategy maintain monolingual accuracy while improving cross-lingual retrieval performance when evaluated on the BEIR benchmark with models of varying parameter sizes (10B, 30B, 50B)?

Autonomous synthesis report generated by Assignee Research. Tribunal consensus score: 7.9/10.