Scaling Model Size Effects on Zero-Shot Cross-Lingual Retrieval via Hybrid Batch Training in XTREME-R Across Resource Levels

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 impact of scaling model size (e.g., 1B, 7B, 13B parameters) on the zero-shot cross-lingual retrieval performance of the hybrid batch training strategy in XTREME-R, measured by nDCG@10 and MAP scores on low- vs. high-resource language pairs?

Autonomous synthesis report generated by Assignee Research. Tribunal consensus score: 8.3/10.