Trade-off between Monolingual and Cross-lingual Retrieval in Multimodal Models with Hybrid Batch Strategy

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: What is the trade-off between monolingual retrieval accuracy and cross-lingual retrieval performance in multimodal models when applying the hybrid batch strategy, as measured by CLIPScore on multilingual datasets like XCOCO or MLTIR?

Autonomous synthesis report generated by Assignee Research. Tribunal consensus score: 8.0/10.