跨语言提示学习中，选对源语言比英语更重要。
When English Isn't the Best Teacher: Source Language Effects in Cross-Lingual In-Context Learning
- 对比多种语言做提示学习，发现非英语源语言更有效
- 在7个任务上验证，语言相似性不是决定因素
- 适合多语言NLP研究者和实际应用开发者
跨语言自然语言处理中的迁移学习已在监督微调中广泛研究，数据可得性和语言相似性是主要影响因素。随着领域转向少样本上下文学习（ICL），人们普遍认为微调的结论可直接适用。但这一假设尚未被严格检验，跨语言ICL中如何选择源语言仍不明确。本文对涵盖7个任务、6个模型及语系多样语言的跨语言迁移进行了大规模实证研究，并分析了生成任务中常见的语言混淆问题。结果表明，基于微调的常规预期在ICL环境下并不一致，需采用新的启发式方法来有效选择源语言。
原文摘要 · Abstract (English)
Cross-lingual transfer in multilingual NLP has been widely explored in supervised fine-tuning contexts, where factors like data availability and linguistic similarity largely determine transfer quality. As the field shifts toward few-shot In-Context Learning (ICL), it is often presumed that insights from fine-tuning carry over unchanged. Yet this assumption has not been rigorously evaluated, leaving open the question of how to choose source languages for cross-lingual ICL. We conduct a broad empirical study of cross-lingual transfer in ICL spanning seven tasks, six models, and a typologically diverse set of languages. We further analyze language confusion, a key obstacle for generative tasks in cross-lingual ICL. Our results show that conventional fine-tuning-based expectations do not consistently apply in the ICL regime and point to alternative heuristics for selecting source languages effectively.
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。