Scaling Domain-Specific Monolingual Data for Zero-Shot Multilingual Retrieval in Hybrid-Trained 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 effect of scaling the size of domain-specific monolingual data on the zero-shot multilingual retrieval performance of hybrid-trained models, evaluated using MRR@10 and NDCG@10 on the MIRACL benchmark?

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