Hybrid Batch Training Sample Ratios for Robust Zero-Shot Cross-Lingual Retrieval in CLIP and ALBEF Models

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 varying the ratio of monolingual, cross-lingual, and multilingual samples in the hybrid batch training strategy on the robustness of CLIP and ALBEF models against adversarial or noisy inputs in zero-shot cross-lingual retrieval tasks?

Autonomous synthesis report generated by Assignee Research. Tribunal consensus score: 8.1/10.