提出多因素平衡的上下文学习方法，提升多语言大模型效果
Balanced Multi-Factor In-Context Learning for Multilingual Large Language Models
- 量化语义、语言对齐和语言性能三因素并动态平衡
- 在mCSQA和TYDI上优于现有方法，跨语言表现更稳
- 适合需要多语言泛化能力的研究与应用
多语言大模型（MLLMs）可通过上下文学习（ICL）在不更新参数的情况下实现高性能，但其效果高度依赖示例选择，尤其在多语言场景中。现有研究指出三个关键影响因素：语义相似性、语言对齐性和语言特异性性能。然而，现有方法分别处理这些因素，未明确解耦其综合影响，导致最优示例选择仍不充分。为此，我们提出平衡多因素上下文学习（BMF-ICL），通过量化并最优平衡三因素实现更优示例选择。在四个MLLM上针对mCSQA和TYDI的数据集实验表明，BMF-ICL显著优于现有方法。进一步分析显示，同时引入三因素及跨语言示例选择至关重要。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。