Scaling Multilingual Model Size for Zero-Shot Cross-Lingual Retrieval Performance

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: To what extent does scaling the model size (e.g., from 7B to 34B parameters) improve the zero-shot cross-lingual retrieval performance of multilingual models trained with the synergistic hybrid batch strategy on the BEIR benchmark suite?

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