LaTeX Compilation: Challenges in the Era of LLMs

2026-03-03 · Tianyou Liu, Ziqiang Li, Xurui Liu, Yu Wu, Yansong Li arxiv

As large language models (LLMs) increasingly assist scientific writing, limitations and the significant token cost of TeX become more and more visible. This paper analyzes TeX's fundamental defects in compilation and user experience design to illustrate its limitations on compilation efficiency, generated semantics, error localization, and tool ecosystem in the era of LLMs. As an alternative, Mogan STEM, a WYSIWYG structured editor, is introduced. Mogan outperforms TeX in the above aspects by its efficient data structure, fast rendering, and on-demand plugin loading. Extensive experiments are conducted to verify the benefits on compilation/rendering time and performance in LLM tasks. Furthermore, we show that due to Mogan's lower information entropy, it is more efficient to use .tmu (the document format of Mogan) to fine-tune LLMs than TeX. Therefore, we launch an appeal for larger experiments on LLM training using the .tmu format.

📄 PDF Abstract BibTeX arXiv:2603.02873

Code (0)

등록된 구현이 없습니다.

TexOCR: Advancing Document OCR Models for Compilable Page-to-LaTeX Reconstruction

2026-04-24 · Chengye Wang, Lin Fu, Zexi Kuang, Yilun Zhao arxiv

Existing document OCR largely targets plain text or Markdown, discarding the structural and executable properties that make LaTeX essential for scientific publishing. We study page-level reconstruction of scientific PDFs…

Reinforcement Learning

TeXpert: A Multi-Level Benchmark for Evaluating LaTeX Code Generation by LLMs

2025-06-20 · Sahil Kale, Vijaykant Nadadur

LaTeX's precision and flexibility in typesetting have made it the gold standard for the preparation of scientific documentation. Large Language Models (LLMs) present a promising opportunity for researchers to produce pub…

Code Generation

LATEX-GCL: Large Language Models (LLMs)-Based Data Augmentation for Text-Attributed Graph Contrastive Learning

2024-09-02 · Haoran Yang, Xiangyu Zhao, Sirui Huang, Qing Li 외

Graph Contrastive Learning (GCL) is a potent paradigm for self-supervised graph learning that has attracted attention across various application scenarios. However, GCL for learning on Text-Attributed Graphs (TAGs) has y…

Contrastive Learning Data Augmentation Graph Learning Language Modelling+1

A Dual-Track Framework for Template-Constrained LaTeX Conversion

2026-06-22 · Chung Cheuk Hei, Liu Li arxiv

With the increasing demands for advanced document conversion, mapping structured Markdown drafts into template-compliant formats like LaTeX remains a challenge. Existing approaches largely depend on either deterministic …

Code as Representation: A Compilable Parsing Paradigm for Academic Documents

2026-08-18 · Rihui Jin, Jun Wang, chengyuan zhu, Liang Mingyu 외 arxiv

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),…