对比TeX与新型编辑器Mogan在大模型时代的优劣
LaTeX Compilation: Challenges in the Era of LLMs
- 用结构化编辑器Mogan替代传统TeX提升编译效率
- Mogan编译速度更快，错误定位更准，支持插件按需加载
- 其文档格式.tmux信息熵更低，更适合微调大模型
随着大语言模型（LLMs）越来越多地辅助科学写作，TeX在编译和用户体验设计上的根本缺陷愈发明显，其在编译效率、生成语义质量、错误定位及工具生态方面均存在局限。本文提出一种名为Mogan STEM的所见即所得结构化编辑器作为替代方案。Mogan通过高效数据结构、快速渲染和按需加载插件，在编译效率、渲染速度与LLM任务表现上显著优于TeX。大量实验验证了其在编译/渲染时间与任务性能上的优势。此外，由于.mtu（Mogan文档格式）具有更低的信息熵，用于微调大模型比TeX更高效。因此，本文呼吁开展更大规模的实验，探索使用.tmux格式训练大模型的可能性。
原文摘要 · Abstract (English)
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.
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。