Impact of Hybrid Batch Training Scaling on Zero-Shot Cross-Lingual Retrieval Performance in Large Multilingual Language 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: What is the impact of scaling the hybrid batch training strategy to larger multilingual language models (e.g., mT5, Bloom) on zero-shot cross-lingual retrieval performance as measured by MRR (Mean Reciprocal Rank) on benchmark datasets like BEIR and CrossLingualFiQA?

Autonomous synthesis report generated by Assignee Research. Tribunal consensus score: 8.2/10.