Hybrid Batch Training for Robust Zero-Shot Multilingual Retrieval Against Domain Shifts

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: How does the proposed hybrid batch training strategy affect the robustness of zero-shot multilingual retrieval performance against domain shifts, as evaluated on the MLQA benchmark with domains from SQuAD, TriviaQA, and NaturalQuestions?

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