Synergistic Optimization for Alignment of Monolingual and Cross-Lingual Representations in Multilingual Models

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: Can the synergistic optimization approach improve the alignment between monolingual and cross-lingual representations in multilingual models, as measured by similarity metrics (e.g., cosine similarity) on the multilingual retrieval task?

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