通过大语言模型的少样本学习实现低资源跨语言摘要
Low-Resource Cross-Lingual Summarization through Few-Shot Learning with Large Language Models
AI总结：
本文研究大语言模型在低资源跨语言摘要中的少样本学习性能，发现少样本学习显著提升GPT-3.5和GPT-4的表现，而Mistral-7B-Instruct-v0.2适应能力有限，并指出需进一步研究专用架构与预训练目标。
摘要：
跨语言摘要（XLS）旨在生成与源语言文档不同的目标语言摘要。尽管大语言模型（LLMs）已展现出有前景的零样本跨语言摘要性能，但它们在该任务上的少样本能力尚未被探索，尤其是对于平行数据有限的低资源语言。本文研究了多种模型的少样本跨语言摘要性能，包括Mistral-7B-Instruct-v0.2、GPT-3.5和GPT-4。实验表明，少样本学习显著提升了LLMs的跨语言摘要性能，特别是在低资源环境下GPT-3.5和GPT-4的性能。然而，开源模型Mistral-7B-Instruct-v0.2在有限示例下难以有效适应跨语言摘要任务。我们的发现凸显了少样本学习在提升跨语言摘要性能方面的潜力，以及针对该任务设计LLM架构和预训练目标进行进一步研究的必要性。我们提供了未来工作方向，以探索更有效的少样本学习策略，并研究LLMs在跨语言摘要中的迁移学习能力。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
