Hybrid Batch Strategy and Language-Agnostic Adversarial Training for Multilingual Robustness on XQuAD Under Distribution Shifts

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 incorporating language-agnostic adversarial training techniques alongside the hybrid batch strategy on the robustness of multilingual language models against cross-lingual retrieval performance degradation under distribution shifts in the XQuAD benchmark?

Autonomous synthesis report generated by Assignee Research. Tribunal consensus score: 8.4/10.