LaTeX Compilation: Challenges in the Era of LLMs
This addresses compilation inefficiencies for researchers and writers using LLMs, though it is incremental as it proposes an alternative tool rather than a fundamental breakthrough.
The paper tackles the limitations of TeX compilation for LLM-assisted scientific writing by introducing Mogan STEM, a WYSIWYG structured editor that outperforms TeX in compilation efficiency, rendering speed, and LLM task performance, with experiments showing benefits in time and lower information entropy for fine-tuning.
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. What's more, 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.