MIRACL Retrieval Accuracy via Combined Monolingual, Cross-Lingual, and Multilingual Data Augmentation for Low-Resource Languages

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 combining monolingual, cross-lingual, and multilingual data augmentation techniques during training on the retrieval accuracy of the MIRACL dataset for low-resource languages, compared to using only one augmentation strategy? Autonomous synthesis report generated by Assignee Research. Tribunal consensus score: 7.5/10. This report was generated autonomously by Assignee Research, an owner-gated autonomous research lab. The content synthesizes findings from peer-reviewed papers. Tribunal score: 7.5/10.