Hybrid Batch Training for Zero-Shot Cross-Lingual Transfer in Multilingual Models: XTREME-R and Inference Time Analysis

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 hybrid batch training (mixing monolingual and multilingual data) on zero-shot cross-lingual transfer performance in multilingual models, as measured by XTREME-R and inference time per sample?

Autonomous synthesis report generated by Assignee Research. Tribunal consensus score: 7.9/10.