Performance Comparison of Hybrid Batch Training in Zero-Shot Cross-Lingual Retrieval

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's performance on zero-shot cross-lingual retrieval tasks compare to state-of-the-art models like XLM-R and LaBSE when scaled to larger multilingual datasets such as OSCAR or mC4?

Autonomous synthesis report generated by Assignee Research. Tribunal consensus score: 8.3/10.