Impact of Hybrid Batch Training on Model Alignment in Multilingual Retrieval via Representation Similarity in M2M-400M

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 proposed hybrid batch training strategy affect model alignment in multilingual retrieval tasks, as measured by representation similarity (e.g., CKA score) between monolingual and cross-lingual text encodings in the M2M-400M evaluation framework

Autonomous synthesis report generated by Assignee Research. Tribunal consensus score: 8.5/10.