对比图文与文本解析策略，为发票处理选型提供实证依据
Multi-Modal Vision vs. Text-Based Parsing: Benchmarking LLM Strategies for Invoice Processing
- 用零样本提示测试八款多模态大模型，分直接图像处理和转markdown解析两种策略
- 原生图文处理整体优于先转文本的结构化方法，不同模型表现差异明显
- 适合需要自动化文档处理的开发者和企业，尤其关注模型选型效率
本文在三个公开发票数据集上，对来自GPT-5、Gemini 2.5和开源Gemma 3三类共八款多模态大语言模型，采用零样本提示进行基准测试。比较了两种处理策略：直接利用多模态能力处理图像，以及先将文档转换为markdown再解析的结构化方法。结果表明，原生图像处理普遍优于结构化方法，且性能表现随模型类型和文档特征变化而异。该基准研究为自动化文档系统中模型与策略的选择提供了实证参考。代码已公开。
原文摘要 · Abstract (English)
This paper benchmarks eight multi-modal large language models from three families (GPT-5, Gemini 2.5, and open-source Gemma 3) on three diverse openly available invoice document datasets using zero-shot prompting. We compare two processing strategies: direct image processing using multi-modal capabilities and a structured parsing approach converting documents to markdown first. Results show native image processing generally outperforms structured approaches, with performance varying across model types and document characteristics. This benchmark provides insights for selecting appropriate models and processing strategies for automated document systems. Our code is available online.
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。