用自监督框架让大模型自己选对例子，跨语言学习更准更快
Align, Generate, Learn: A Novel Closed-Loop Framework for Cross-Lingual In-Context Learning
- 大模型自我筛选任务相关例句，不依赖外部工具
- 在多语言基准上超越现有方法，低资源语言表现尤佳
- 适合需要跨语言泛化能力的AI应用开发
跨语言上下文学习（XICL）已成为利用大语言模型应对多语言任务的变革性范式，尤其适用于低资源语言。然而，现有方法常依赖外部检索器或任务特定微调，限制了可扩展性和泛化能力。本文提出一种新型自监督框架，利用大模型的生成能力内部选择并使用任务相关示例。该方法引入两个关键目标：检索-生成对齐损失以优化所选示例质量，以及语义一致性损失以保证跨语言一致性。在多语言基准上的广泛实验表明，该方法达到当前最优性能，显著优于现有基线。进一步分析显示其在不同语系间均具鲁棒性，并能泛化至未见任务。人工评估确认本方法生成结果在流畅性、相关性和语义正确性方面均更优。这项工作为跨语言上下文学习提供了可扩展、高效且通用的解决方案。
原文摘要 · Abstract (English)
Cross-lingual in-context learning (XICL) has emerged as a transformative paradigm for leveraging large language models (LLMs) to tackle multilingual tasks, especially for low-resource languages. However, existing approaches often rely on external retrievers or task-specific fine-tuning, limiting their scalability and generalizability. In this paper, we propose a novel self-supervised framework that harnesses the generative capabilities of LLMs to internally select and utilize task-relevant examples. Our method introduces two key objectives: a retrieval-generation alignment loss to optimize the quality of selected examples and a semantic coherence loss to ensure cross-lingual consistency. Through extensive experiments on multilingual benchmarks, our approach achieves state-of-the-art performance, significantly outperforming existing baselines. Further analysis highlights its robustness across diverse language families and its ability to generalize to unseen tasks. Human evaluations confirm the superior fluency, relevance, and semantic correctness of outputs generated by our method. This work provides a scalable, effective, and generalizable solution for cross-lingual in-context learning.
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。