Hybrid Batch Training for Efficient Cross-Lingual Inference with Zero-Shot Performance

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: Can hybrid batch training with both monolingual and multilingual intermediate tasks improve inference efficiency (measured in tokens/s) on cross-lingual tasks while maintaining zero-shot performance on XTREME, compared to sequential fine-tuning?

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