Model Size Scaling and Monolingual-Crosslingual Retrieval Trade-offs in Hybrid Batch TyDi QA

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 effect of scaling the model size (e.g., 7B, 13B, 34B) on the trade-off between monolingual and cross-lingual retrieval performance when using the hybrid batch strategy on the TyDi QA benchmark?

Autonomous synthesis report generated by Assignee Research. Tribunal consensus score: 7.5/10.