Scaling Hybrid Batch Training in M2M100: NDCG@10 Degradation Across MTEB Zero-Shot Cross-Lingual Retrieval Benchmarks

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 scale with increasing numbers of languages in the M2M100 model, as measured by NDCG@10 performance degradation across MTEB's zero-shot cross-lingual retrieval benchmarks?

Autonomous synthesis report generated by Assignee Research. Tribunal consensus score: 8.2/10.