Balanced Multi-Factor In-Context Learning for Multilingual Large Language Models
This work addresses the challenge of optimizing example selection for multilingual in-context learning, which is incremental as it builds on known factors but combines them in a novel way.
The paper tackles the problem of example selection sensitivity in multilingual in-context learning for large language models by proposing a method that balances semantic similarity, linguistic alignment, and language-specific performance, resulting in improved performance over existing methods on datasets like mCSQA and TYDI across four models.
Multilingual large language models (MLLMs) are able to leverage in-context learning (ICL) to achieve high performance by leveraging cross-lingual knowledge transfer without parameter updates. However, their effectiveness is highly sensitive to example selection, particularly in multilingual settings. Based on the findings of existing work, three key factors influence multilingual ICL: (1) semantic similarity, (2) linguistic alignment, and (3) language-specific performance. However, existing approaches address these factors independently, without explicitly disentangling their combined impact, leaving optimal example selection underexplored. To address this gap, we propose balanced multi-factor ICL (\textbf{BMF-ICL}), a method that quantifies and optimally balances these factors for improved example selection. Experiments on mCSQA and TYDI across four MLLMs demonstrate that BMF-ICL outperforms existing methods. Further analysis highlights the importance of incorporating all three factors and the importance of selecting examples from multiple languages.