Hybrid Batch Optimization in Multilingual Models for Zero-Shot Code Retrieval Performance

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 simultaneous optimization of monolingual and cross-lingual objectives in a hybrid batch training strategy impact the zero-shot performance of multilingual language models on code-related retrieval tasks compared to natural language benchmarks like MSCOCO when evaluated using metrics such as Mean Reciprocal Rank (MRR) and Recall@K?

Autonomous synthesis report generated by Assignee Research. Tribunal consensus score: 7.9/10.