Large language models (LLMs), such as GPT-3 and ChatGPT, have demonstrated remarkable results in various natural language processing (NLP) tasks with in-context learning, which involves inference based on a few demonstration examples. Despite their successes in NLP tasks, no investigation has been conducted to assess the ability of LLMs to perform document information extraction (DIE) using in-context learning. Applying LLMs to DIE poses two challenges: the modality and task gap. To this end, we propose a simple but effective in-context learning framework called ICL-D3IE, which enables LLMs to perform DIE with different types of demonstration examples. Specifically, we extract the most difficult and distinct segments from hard training documents as hard demonstrations for benefiting all test instances. We design demonstrations describing relationships that enable LLMs to understand positional relationships. We introduce formatting demonstrations for easy answer extraction. Additionally, the framework improves diverse demonstrations by updating them iteratively. Our experiments on three widely used benchmark datasets demonstrate that the ICL-D3IE framework enables GPT-3/ChatGPT to achieve superior performance when compared to previous pre-trained methods fine-tuned with full training in both the in-distribution (ID) setting and in the out-of-distribution (OOD) setting.

翻译：大型语言模型（LLMs），如GPT-3和ChatGPT，通过上下文学习（即在少量演示示例基础上进行推理）已在多种自然语言处理任务中展现出卓越性能。尽管在NLP任务中取得了成功，但尚未有研究评估LLMs通过上下文学习执行文档信息抽取（DIE）的能力。将LLMs应用于DIE面临两大挑战：模态差异与任务鸿沟。为此，我们提出一种简单而有效的上下文学习框架ICL-D3IE，使LLMs能够利用不同类型的演示示例执行DIE。具体而言，我们从困难训练文档中提取最复杂且最具区分性的片段作为硬演示示例，以惠及所有测试实例；设计描述位置关系的演示示例以帮助LLMs理解空间关联；引入格式化演示示例以简化答案提取。此外，该框架通过迭代更新机制持续优化多样化演示示例。在三个广泛使用的基准数据集上的实验表明，无论是在分布内（ID）设置还是分布外（OOD）设置下，ICL-D3IE框架均能使GPT-3/ChatGPT在性能上超越先前需全量微调的预训练方法。