.tmu: A Low-Entropy Tree-Structured Representation for LLM-Assisted Scientific Writing

Title:.tmu: A Low-Entropy Tree-Structured Representation for LLM-Assisted Scientific Writing

Abstract:As large language models (LLMs) increasingly assist scientific writing, the limitations and token costs of generating TeX become increasingly visible. This paper analyzes TeX's architectural mismatch with LLM workflows, stemming from its lack of an explicit structural representation, to illustrate its limitations on generated semantics and error localization. As an alternative, we introduce .tmu, a low-entropy tree-structured representation. With its efficient data structure and clear contextual boundaries, .tmu outperforms .tex in the above aspects. Experiments across four LLMs provide evidence for this claim in most evaluated settings. Furthermore, we show that due to its lower information entropy, fine-tuning LLMs on .tmu achieves approximately 43% lower final training loss than on .tex. Our work provides a more scalable and LLM-friendly data representation for LLM-assisted scientific writing.

24 pages, 8 figures. To be published in EMNLP 2026

Computation and Language (cs.CL)

arXiv:2603.02873 [cs.CL]

(or arXiv:2603.02873v5 [cs.CL] for this version)

https://doi.org/10.48550/arXiv.2603.02873 Focus to learn more arXiv-issued DOI via DataCite

arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.

Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.

Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.