Cross-lingual summarization (XLS) aims to generate a summary in a target
language different from the source language document. While large language
models (LLMs) have shown promising zero-shot XLS performance, their few-shot
capabilities on this task remain unexplored, especially for low-resource
languages with limited parallel data. In this paper, we investigate the
few-shot XLS performance of various models, including Mistral-7B-Instruct-v0.2,
GPT-3.5, and GPT-4. Our experiments demonstrate that few-shot learning
significantly improves the XLS performance of LLMs, particularly GPT-3.5 and
GPT-4, in low-resource settings. However, the open-source model
Mistral-7B-Instruct-v0.2 struggles to adapt effectively to the XLS task with
limited examples. Our findings highlight the potential of few-shot learning for
improving XLS performance and the need for further research in designing LLM
architectures and pre-training objectives tailored for this task. We provide a
future work direction to explore more effective few-shot learning strategies
and to investigate the transfer learning capabilities of LLMs for cross-lingual
summarization.

跨语种摘要生成（XLS）旨在在与源语言文档不同的目标语言中生成摘要。我们研究了各种模型的少样本学习（few-shot learning）在 XLS 任务中的表现，并发现少样本学习显著提高了 LLMs 在低资源环境中的 XLS 性能，特别是 GPT-3.5 和 GPT-4。然而，开源模型 Mistral-7B-Instruct-v0.2 在有限的示例中有效适应 XLS 任务方面存在困难。我们的研究结果突出了少样本学习提高 XLS 性能的潜力，以及在设计专为该任务定制的 LLMs 架构和预训练目标方面需要进一步研究。我们提出了未来的研究方向，探索更有效的少样本学习策略，并调查 LLMs 在跨语种摘要生成中的迁移学习能力。