代码作为表示：学术文档的可编译解析范式
Code as Representation: A Compilable Parsing Paradigm for Academic Documents
浏览论文内容
中文总结 AI 辅助
针对学术PDF难以被机器处理的问题，提出CADP可编译解析范式，构建CADP-Bench基准并测试SOTA MLLMs，发现前沿模型仍难生成高保真可执行重构，该基准已开放供研究。
中文摘要 AI 辅助
学术论文是科学知识的主要载体，但大部分知识仍被锁定在专为人类阅读而非机器使用优化的PDF中。对于多模态大语言模型（MLLMs），核心挑战不仅是感知，更是表示：学术页面将文本与结构化学术元素（SAEs）（如表、公式、图表、伪代码）交织在一起，其结构、数据和逻辑难以被Markdown等常见替代方案保留。为此，我们提出可编译学术文档解析（CADP）范式，将完整页面重构为上下文LaTeX加可执行Python，从而可重构结构保留元素与可执行图表表示，再重新编译并与源页面直接验证。为支持该设置，我们引入CADP-Bench，这是一个经专家验证的完整学术页面基准，包含紧密耦合的文本与多种SAE类型，通过重注入编译协议进行评估。我们进一步研究了当前最先进（SOTA）MLLMs及结合常见智能体技术的探索性多智能体基线的能力。结果显示，即使是前沿模型仍难以生成高保真的可执行重构，凸显了结构感知型科学文档解析领域仍有巨大改进空间。CADP-Bench已发布供未来研究使用。
英文摘要
Academic papers are a primary carrier of scientific knowledge, yet most of this knowledge remains locked in PDFs that are optimized for human reading rather than machine use. For Multimodal Large Language Models (MLLMs), the core challenge is not only perception, but representation: scientific pages interleave text with Structured Academic Elements (SAEs) such as tables, formulas, charts, and pseudocode, whose structure, data, and logic are poorly preserved by common surrogates like Markdown. We therefore propose Compilable Academic Document Parsing (CADP), a paradigm that reconstructs a full page as contextual \LaTeX{} plus executable Python, so that structure-preserving elements and executable chart representations can be reconstructed, recompiled, and directly verified against the source page. To support this setting, we introduce CADP-Bench, an expert-verified benchmark of full academic pages containing tightly coupled text and multiple SAE types, evaluated through a re-injection compilation protocol. We further study current capabilities using SOTA MLLMs and an exploratory multi-agent baseline that incorporates common agentic techniques. Results show that even frontier models still struggle to produce high-fidelity executable reconstructions, highlighting substantial room for improvement in structure-aware scientific document parsing. CADP-Bench is released for future research.
发表机构
- Southeast University（东南大学）
- Nanyang Technological University（南洋理工大学）
- Nanjing University（南京大学）
机构由 AI 辅助整理，请以论文原文为准。
