Hybrid Batch Training vs. Multilingual Contrastive Fine-Tuning for Zero-Shot Cross-Lingual Retrieval Accuracy

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 hybrid batch training strategy compare to fine-tuning with multilingual contrastive loss on zero-shot cross-lingual retrieval accuracy across both in-domain (TyDiQA-GoldP) and out-of-domain (MLQA) datasets?

Autonomous synthesis report generated by Assignee Research. Tribunal consensus score: 7.8/10.