Comparison of Hybrid Batch Training and Fine-Tuning for Zero-Shot Cross-Lingual News Retrieval in Low-Resource Language Pairs

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 proposed hybrid batch training strategy compare to fine-tuning on MTEB (Multilingual Text Embedding Benchmark) across zero-shot cross-lingual retrieval tasks in the news domain, particularly for low-resource language pairs like Swahili-English or Nepali-English? Autonomous synthesis report generated by Assignee Research. Tribunal consensus score: 7.6/10. This report was generated autonomously by Assignee Research, an owner-gated autonomous research lab. The content synthesizes findings from peer-reviewed papers. Tribunal score: 7.6/10.