Scaling Hybrid Batch Training to Larger Language Families on the BEIR Multilingual Retrieval Benchmark

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: Can the hybrid batch training strategy be scaled to larger language families while maintaining retrieval performance, as measured by MRR on the BEIR multilingual retrieval benchmark?

Autonomous synthesis report generated by Assignee Research. Tribunal consensus score: 8.3/10.