让大模型读懂含表格的长文档，提出框架与数据集
Extract Information from Hybrid Long Documents Leveraging LLMs: A Framework and Dataset
- 设计自动化信息提取框架，处理超长混合文档
- 发现简单表格序列化即可让大模型理解表格内容
- 提供可复用的提示工程方法，适合金融等复杂场景
大型语言模型在文本理解和表格推理任务中表现优异，但对包含文本和表格的混合内容（即混合长文档，HLD）的处理能力尚未探索。由于HLD远超大模型的上下文长度限制，本文提出自动化信息提取框架（AIE），用于处理此类文档，并实验分析了四个关键信息提取方面：1）有效选择并摘要HLD中有用部分；2）简单的表格序列化方式足以让大模型理解表格；3）基础AIE在多种复杂场景下具备良好适应性；4）有效的提示工程可显著提升大模型在HLD上的表现。为解决HLD数据集稀缺问题，本文还构建了金融报告数值提取（FINE）数据集。代码与数据已公开。
原文摘要 · Abstract (English)
Large Language Models (LLMs) demonstrate exceptional performance in textual understanding and tabular reasoning tasks. However, their ability to comprehend and analyze hybrid text, containing textual and tabular data, remains unexplored. The hybrid text often appears in the form of hybrid long documents (HLDs), which far exceed the token limit of LLMs. Consequently, we apply an Automated Information Extraction framework (AIE) to enable LLMs to process the HLDs and carry out experiments to analyse four important aspects of information extraction from HLDs. Given the findings: 1) The effective way to select and summarize the useful part of a HLD. 2) An easy table serialization way is enough for LLMs to understand tables. 3) The naive AIE has adaptability in many complex scenarios. 4) The useful prompt engineering to enhance LLMs on HLDs. To address the issue of dataset scarcity in HLDs and support future work, we also propose the Financial Reports Numerical Extraction (FINE) dataset. The dataset and code are publicly available in the attachments.
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。