Hybrid Batch Training Effects on Monolingual-Crosslingual Retrieval Trade-offs in Multilingual Encoders

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 strategy influence the trade-off between monolingual and cross-lingual retrieval accuracy when fine-tuning a multilingual encoder with different percentages of monolingual vs. cross-lingual training data, evaluated using BEIR and XNLI benchmarks?

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