Hybrid Batch Training with Curriculum Learning for Robust Monolingual Retrieval in MIRACL

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: To what extent does the proposed hybrid batch training strategy with curriculum learning enhance the robustness of monolingual retrieval performance across different domains in the MIRACL benchmark, as measured by MRR?

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