Multilingual Contrastive Learning for Zero-Shot Cross-Lingual Retrieval on XNLI

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 addition of multilingual contrastive learning objectives in hybrid batch training affect zero-shot cross-lingual retrieval performance on the XNLI benchmark, measured by accuracy and F1 scores across low-resource languages?

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