Impact of Hybrid Batch Training on Zero-Shot Cross-Lingual Retrieval Accuracy in BEIR 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: What is the impact of hybrid batch training on zero-shot cross-lingual retrieval accuracy when evaluated across different language pairs (e.g., high-resource vs. low-resource languages) in the BEIR benchmark, and how does it scale with model size beyond 7B parameters?

Autonomous synthesis report generated by Assignee Research. Tribunal consensus score: 7.5/10.