Hybrid Batch Training for Robust Zero-Shot Cross-Lingual Retrieval Under Domain Shift on XTREME

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: Does the hybrid batch training strategy improve robustness to domain shifts in zero-shot cross-lingual retrieval, as measured by performance degradation on the XTREME benchmark when evaluated on out-of-domain queries?

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