Performance of SWIM-IR-Trained Multilingual Dense Retrievers on Low-Resource Languages in BEIR Across Language Families

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 do multilingual dense retrievers trained on SWIM-IR perform on low-resource languages in BEIR compared to models trained on natural multilingual datasets, when evaluated using precision@k and recall@k metrics across different language families?

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