Scaling Hybrid Batch Training with Contrastive Objectives for Multilingual Retrieval and Zero-Shot Cross-Lingual Generalization

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: Does combining the hybrid batch training strategy with contrastive learning objectives (e.g., SimCSE) further improve multilingual retrieval performance on BEIR while maintaining zero-shot cross-lingual generalization, and how does it scale with model size?

Autonomous synthesis report generated by Assignee Research. Tribunal consensus score: 7.7/10.