用预处理工具提升大模型对复杂金融文档的理解能力
On the Comprehensibility of Multi-structured Financial Documents using LLMs and Pre-processing Tools
- 引入预处理工具清理和结构化金融文档中的复杂数据
- GPT-4o直接处理准确率仅56%，加入预处理后达61.3%
- 该方法显著降低错误率，适合金融、审计等高精度场景
混合来源（如PDF与网页）中复杂结构化数据的泛滥给当前大语言模型（LLM）和多模态大语言模型（MLLM）带来挑战，难以准确回答包含嵌套表格、多维图表等复杂结构的问题，常导致幻觉和错误输出。本文研究利用工业级与开源预处理工具构建流水线，提升LLM和MLLM对金融文档复杂结构的理解能力。实验表明，直接输入文档时GPT-4o在多结构文档上的准确率为56%；加入预处理后，其准确率提升至61.3%，GPT-4更达76%，且整体成本更低。代码已公开于https://github.com/OGCDS/FinancialQA。
原文摘要 · Abstract (English)
The proliferation of complex structured data in hybrid sources, such as PDF documents and web pages, presents unique challenges for current Large Language Models (LLMs) and Multi-modal Large Language Models (MLLMs) in providing accurate answers. Despite the recent advancements of MLLMs, they still often falter when interpreting intricately structured information, such as nested tables and multi-dimensional plots, leading to hallucinations and erroneous outputs. This paper explores the capabilities of LLMs and MLLMs in understanding and answering questions from complex data structures found in PDF documents by leveraging industrial and open-source tools as part of a pre-processing pipeline. Our findings indicate that GPT-4o, a popular MLLM, achieves an accuracy of 56% on multi-structured documents when fed documents directly, and that integrating pre-processing tools raises the accuracy of LLMs to 61.3% for GPT-4o and 76% for GPT-4, and with lower overall cost. The code is publicly available at https://github.com/OGCDS/FinancialQA.
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。