Hybrid Batch Training for Zero-Shot Multilingual Retrieval on Domain-Shifted XWIKI Datasets

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 the hybrid batch training approach maintain its effectiveness in zero-shot multilingual retrieval performance when evaluated on domain-shifted datasets like XWIKI, as compared to standard multilingual fine-tuning evaluated using MRR scores?

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