Scaling Hybrid Batch Training from 7B to 30B Parameters: Monolingual Accuracy and Cross-Lingual Retrieval Trade-offs on BEIR and

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 scale with increasing model size (e.g., 7B to 30B parameters) in terms of BEIR and NQ benchmark trade-offs between monolingual accuracy and cross-lingual retrieval performance?

Autonomous synthesis report generated by Assignee Research. Tribunal consensus score: 7.8/10.