Impact of Dynamic Batch Composition on XLM-R's Zero-Shot 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: What is the impact of dynamic batch composition strategies (e.g., mixing monolingual/cross-lingual samples by language similarity) on XLM-R's zero-shot retrieval accuracy and robustness across BEIR multilingual benchmarks?

Autonomous synthesis report generated by Assignee Research. Tribunal consensus score: 8.5/10.