Hybrid Batch Training for Robust Zero-Shot Retrieval with Noisy Code-Switching Queries

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 zero-shot retrieval robustness to noisy code-switching queries in the BEIR benchmark compared to monolingual fine-tuning, as measured by changes in nDCG@3 scores across domains?

Autonomous synthesis report generated by Assignee Research. Tribunal consensus score: 8.2/10.