Hybrid Batch Training Strategy for Stable Retrieval Performance Across Domain-Shifted MLDR Evaluations

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 proposed hybrid batch training strategy maintain retrieval performance stability across domain-shifted evaluations on the MLDR benchmark when compared to monolingual-only optimized models?

Autonomous synthesis report generated by Assignee Research. Tribunal consensus score: 8.0/10.