@inproceedings{le-etal-2026-scholawrite,
title = "{S}chola{W}rite: A Dataset of End-to-End Scholarly Writing",
author = "Le, Khanh Chi and
Wang, Linghe and
Lee, Minhwa and
Volkov, Ross and
Chau, Luan Tuyen and
Kang, Dongyeop",
editor = "Liakata, Maria and
Moreira, Viviane P. and
Zhang, Jiajun and
Jurgens, David",
booktitle = "Proceedings of the 64th Annual Meeting of the {A}ssociation for {C}omputational {L}inguistics (Volume 1: Long Papers)",
month = jul,
year = "2026",
address = "San Diego, California, United States",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.acl-long.1606/",
pages = "34755--34788",
ISBN = "979-8-89176-390-6",
abstract = "Writing is a cognitively demanding activity that requires constant decision-making, heavy reliance on working memory, and frequent shifts between tasks of different goals. To build writing assistants that truly align with writers' cognition, it is necessary to capture and analyze the complete thought process behind how writers transform ideas into final texts. We present SCHOLAWRITE, the first dataset of end-to-end scholarly writing, tracing the multi-month journey from initial drafts to final manuscripts. The dataset traces nearly 62K LaTeX-based edits from five computer science preprints over four months and is enriched with fine-grained annotations of cognitive writing intentions. We demonstrate the value of ScholaWrite through three complementary contributions: (1) analysis of real-world writing behavior reveals that scholarly writing is highly non-linear and multi-intentional, blending rapid drafting bursts with cognitively sustained writing sessions; (2) evaluations of current large language models show that they struggle to provide meaningful support throughout the human writing process; and (3) models finetuned on SCHOLAWRITE demonstrate improved alignment with human writing workflows. SCHOLAWRITE underscores the value of capturing scientists' cognitive writing process and provides actionable insights and resources for the development of future writing assistants."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="le-etal-2026-scholawrite">
<titleInfo>
<title>ScholaWrite: A Dataset of End-to-End Scholarly Writing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Khanh</namePart>
<namePart type="given">Chi</namePart>
<namePart type="family">Le</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Linghe</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Minhwa</namePart>
<namePart type="family">Lee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ross</namePart>
<namePart type="family">Volkov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Luan</namePart>
<namePart type="given">Tuyen</namePart>
<namePart type="family">Chau</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dongyeop</namePart>
<namePart type="family">Kang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Maria</namePart>
<namePart type="family">Liakata</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Viviane</namePart>
<namePart type="given">P</namePart>
<namePart type="family">Moreira</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jiajun</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">David</namePart>
<namePart type="family">Jurgens</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">San Diego, California, United States</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-390-6</identifier>
</relatedItem>
<abstract>Writing is a cognitively demanding activity that requires constant decision-making, heavy reliance on working memory, and frequent shifts between tasks of different goals. To build writing assistants that truly align with writers’ cognition, it is necessary to capture and analyze the complete thought process behind how writers transform ideas into final texts. We present SCHOLAWRITE, the first dataset of end-to-end scholarly writing, tracing the multi-month journey from initial drafts to final manuscripts. The dataset traces nearly 62K LaTeX-based edits from five computer science preprints over four months and is enriched with fine-grained annotations of cognitive writing intentions. We demonstrate the value of ScholaWrite through three complementary contributions: (1) analysis of real-world writing behavior reveals that scholarly writing is highly non-linear and multi-intentional, blending rapid drafting bursts with cognitively sustained writing sessions; (2) evaluations of current large language models show that they struggle to provide meaningful support throughout the human writing process; and (3) models finetuned on SCHOLAWRITE demonstrate improved alignment with human writing workflows. SCHOLAWRITE underscores the value of capturing scientists’ cognitive writing process and provides actionable insights and resources for the development of future writing assistants.</abstract>
<identifier type="citekey">le-etal-2026-scholawrite</identifier>
<location>
<url>https://aclanthology.org/2026.acl-long.1606/</url>
</location>
<part>
<date>2026-07</date>
<extent unit="page">
<start>34755</start>
<end>34788</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T ScholaWrite: A Dataset of End-to-End Scholarly Writing
%A Le, Khanh Chi
%A Wang, Linghe
%A Lee, Minhwa
%A Volkov, Ross
%A Chau, Luan Tuyen
%A Kang, Dongyeop
%Y Liakata, Maria
%Y Moreira, Viviane P.
%Y Zhang, Jiajun
%Y Jurgens, David
%S Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
%D 2026
%8 July
%I Association for Computational Linguistics
%C San Diego, California, United States
%@ 979-8-89176-390-6
%F le-etal-2026-scholawrite
%X Writing is a cognitively demanding activity that requires constant decision-making, heavy reliance on working memory, and frequent shifts between tasks of different goals. To build writing assistants that truly align with writers’ cognition, it is necessary to capture and analyze the complete thought process behind how writers transform ideas into final texts. We present SCHOLAWRITE, the first dataset of end-to-end scholarly writing, tracing the multi-month journey from initial drafts to final manuscripts. The dataset traces nearly 62K LaTeX-based edits from five computer science preprints over four months and is enriched with fine-grained annotations of cognitive writing intentions. We demonstrate the value of ScholaWrite through three complementary contributions: (1) analysis of real-world writing behavior reveals that scholarly writing is highly non-linear and multi-intentional, blending rapid drafting bursts with cognitively sustained writing sessions; (2) evaluations of current large language models show that they struggle to provide meaningful support throughout the human writing process; and (3) models finetuned on SCHOLAWRITE demonstrate improved alignment with human writing workflows. SCHOLAWRITE underscores the value of capturing scientists’ cognitive writing process and provides actionable insights and resources for the development of future writing assistants.
%U https://aclanthology.org/2026.acl-long.1606/
%P 34755-34788
Markdown (Informal)
[ScholaWrite: A Dataset of End-to-End Scholarly Writing](https://aclanthology.org/2026.acl-long.1606/) (Le et al., ACL 2026)
ACL
- Khanh Chi Le, Linghe Wang, Minhwa Lee, Ross Volkov, Luan Tuyen Chau, and Dongyeop Kang. 2026. ScholaWrite: A Dataset of End-to-End Scholarly Writing. In Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 34755–34788, San Diego, California, United States. Association for Computational Linguistics.