@inproceedings{liu-etal-2026-tmu,
title = ".tmu: A Low-Entropy Tree-Structured Representation for {LLM}-Assisted Scientific Writing",
author = "Liu, Tianyou and
Li, Ziqiang and
Liu, Xurui and
Wu, Yu and
Li, Yansong",
editor = "Atanasova, Pepa and
Haffari, Gholamreza and
Wang, Minghan",
booktitle = "Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing: Industry Track",
month = oct,
year = "2026",
address = "Budapest, Hungary",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.emnlp-industry.8/",
pages = "100--123",
ISBN = "979-8-89176-460-6",
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."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="liu-etal-2026-tmu">
<titleInfo>
<title>.tmu: A Low-Entropy Tree-Structured Representation for LLM-Assisted Scientific Writing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Tianyou</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ziqiang</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xurui</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yu</namePart>
<namePart type="family">Wu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yansong</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-10</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing: Industry Track</title>
</titleInfo>
<name type="personal">
<namePart type="given">Pepa</namePart>
<namePart type="family">Atanasova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Gholamreza</namePart>
<namePart type="family">Haffari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Minghan</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Budapest, Hungary</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-460-6</identifier>
</relatedItem>
<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.</abstract>
<identifier type="citekey">liu-etal-2026-tmu</identifier>
<location>
<url>https://aclanthology.org/2026.emnlp-industry.8/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>100</start>
<end>123</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T .tmu: A Low-Entropy Tree-Structured Representation for LLM-Assisted Scientific Writing
%A Liu, Tianyou
%A Li, Ziqiang
%A Liu, Xurui
%A Wu, Yu
%A Li, Yansong
%Y Atanasova, Pepa
%Y Haffari, Gholamreza
%Y Wang, Minghan
%S Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing: Industry Track
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-460-6
%F liu-etal-2026-tmu
%X 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.
%U https://aclanthology.org/2026.emnlp-industry.8/
%P 100-123
Markdown (Informal)
[.tmu: A Low-Entropy Tree-Structured Representation for LLM-Assisted Scientific Writing](https://aclanthology.org/2026.emnlp-industry.8/) (Liu et al., EMNLP 2026)
ACL