Search papers, labs, and topics across Lattice.
This paper introduces Compilable Academic Document Parsing (CADP), a novel paradigm that transforms academic papers into contextual \LaTeX{} and executable Python to preserve and verify the structure of Structured Academic Elements (SAEs). The authors present CADP-Bench, a benchmark designed to evaluate the parsing capabilities of Multimodal Large Language Models (MLLMs) on full academic pages, revealing that even state-of-the-art models struggle with high-fidelity reconstructions. The findings underscore the need for improved methods in structure-aware scientific document parsing, as current approaches fall short in accurately representing complex academic content.
Even state-of-the-art MLLMs fail to accurately reconstruct academic documents, revealing a critical gap in machine understanding of scientific knowledge.
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.
