ALBEF Model Robustness Against Adversarial Attacks in Zero-Shot Cross-Lingual Retrieval Under Hybrid Training Batch Size Scaling

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 scaling of batch size in hybrid training (monolingual, cross-lingual, multilingual) impact the robustness of ALBEF models against adversarial attacks in zero-shot cross-lingual retrieval, as evaluated by accuracy on XNLI and MLDoc?

Autonomous synthesis report generated by Assignee Research. Tribunal consensus score: 7.7/10.