Blessing of Multilinguality: A Systematic Analysis of Multilingual In-Context Learning
This work addresses the performance gap for underrepresented languages in AI, offering a strategic method to enhance cross-lingual transfer, though it is incremental as it builds on existing prompting strategies.
The paper tackles the underperformance of multilingual large language models on low-resource languages by systematically analyzing multilingual in-context learning, showing that using demonstrations in high-resource languages consistently improves performance, especially for low-resource language tasks, with measurable gains from multilingual exposure.
While multilingual large language models generally perform adequately, and sometimes even rival English performance on high-resource languages (HRLs), they often significantly underperform on low-resource languages (LRLs). Among several prompting strategies aiming at bridging the gap, multilingual in-context learning (ICL) has been particularly effective when demonstration in target languages is unavailable. However, there lacks a systematic understanding of when and why it works well. In this work, we systematically analyze multilingual ICL, using demonstrations in HRLs to enhance cross-lingual transfer. We show that demonstrations in mixed HRLs consistently outperform English-only ones across the board, particularly for tasks written in LRLs. Surprisingly, our ablation study shows that the presence of irrelevant non-English sentences in the prompt yields measurable gains, suggesting the effectiveness of multilingual exposure itself. Our results highlight the potential of strategically leveraging multilingual resources to bridge the performance gap for underrepresented languages.