Scaling Domain-Specific Augmented Data in Hybrid Batch Training for BEIR 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 scaling the size of domain-specific augmented data on the trade-off between monolingual and cross-lingual retrieval performance in hybrid batch training strategies on the BEIR benchmark?

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