Trade-off between Batch Size and Computational Efficiency in Hybrid Batch Training for BEIR Retrieval

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: What is the trade-off between batch size and computational efficiency (measured in tokens per second on A100 GPUs) when optimizing hybrid batch training for simultaneous monolingual and cross-lingual retrieval on BEIR benchmark datasets?

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