Scaling Training Languages to Narrow Zero-Shot Cross-Lingual Retrieval Gaps Between Hybrid Batch and Standard Multilingual

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 number of training languages on the zero-shot cross-lingual retrieval performance gap between the hybrid batch strategy and standard multilingual fine-tuning, as measured by MRR@10 on XQuAD and MLQA benchmarks?

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