Multilingual Pre-trained Language Model Performance in Zero-Shot Retrieval with Hybrid Batch Training

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 impact of different multilingual pre-trained language models (e.g., mBERT, XLM-R, LaBSE) on zero-shot retrieval performance when using the proposed hybrid batch training strategy on long-context subsets of BEIR?

Autonomous synthesis report generated by Assignee Research. Tribunal consensus score: 7.6/10.