ParseBench：面向AI代理的文档解析基准测试
ParseBench: A Document Parsing Benchmark for AI Agents
AI总结：
本文提出ParseBench，一个包含2000多页企业文档的基准测试，涵盖表格、图表、内容忠实度、语义格式和视觉关联五大能力维度，揭示了当前系统在这些方面的能力缺口。
摘要：
AI代理正在改变文档解析的要求。关键在于语义正确性：解析输出必须保留用于自主决策所需结构和意义，包括正确的表格结构、精确的图表数据、语义明确的格式和视觉关联。现有基准测试未能充分捕捉企业自动化场景，依赖狭窄的文档分布和文本相似性指标，遗漏了代理关键失败。我们引入ParseBench，包含约2000页经人类验证的企业文档，涵盖保险、金融和政府领域，围绕表格、图表、内容忠实度、语义格式和视觉关联五个能力维度组织。在14种方法上，包括视觉语言模型、专用文档解析器和LlamaParse，基准测试揭示了能力碎片化：没有方法在所有五个维度上都表现优异。LlamaParse Agentic在总体得分上最高，达到84.9%，基准测试突显了当前系统在这些方面的剩余能力缺口。数据集和评估代码可在https://huggingface.co/datasets/llamaindex/ParseBench和https://github.com/run-llama/ParseBench上获取。
英文摘要：
AI agents are changing the requirements for document parsing. What matters is semantic correctness: parsed output must preserve the structure and meaning needed for autonomous decisions, including correct table structure, precise chart data, semantically meaningful formatting, and visual grounding. Existing benchmarks do not fully capture this setting for enterprise automation, relying on narrow document distributions and text-similarity metrics that miss agent-critical failures. We introduce ParseBench, a benchmark of ${\sim}2{,}000$ human-verified pages from enterprise documents spanning insurance, finance, and government, organized around five capability dimensions: tables, charts, content faithfulness, semantic formatting, and visual grounding. Across 14 methods spanning vision-language models, specialized document parsers, and LlamaParse, the benchmark reveals a fragmented capability landscape: no method is consistently strong across all five dimensions. LlamaParse Agentic achieves the highest overall score at 84.9%, and the benchmark highlights the remaining capability gaps across current systems. Dataset and evaluation code are available on https://huggingface.co/datasets/llamaindex/ParseBench and https://github.com/run-llama/ParseBench.
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。
