Performance of Hybrid Batch Training on MIRACL Benchmark for Zero-Shot Cross-Lingual Retrieval

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: How does the hybrid batch training strategy's performance on the MIRACL benchmark compare to state-of-the-art multilingual models (e.g., XLM-R, LaBSE) in terms of zero-shot cross-lingual retrieval accuracy (MAP, NDCG) across low-resource language pairs?

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