Comparison of Hybrid Batch Training and Contrastive Learning for Zero-Shot Cross-Lingual Retrieval on M2C2 Benchmark

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 contrastive learning in improving zero-shot cross-lingual retrieval performance on the M2C2 benchmark when scaling from 13B to 130B parameters, measured by MAP@10 and recall@50?

Autonomous synthesis report generated by Assignee Research. Tribunal consensus score: 7.9/10.