ScholaWrite: A Dataset of End-to-End Scholarly Writing Process

ACL ARR 2026 January Submission3031 Authors

Keywords: corpus creation, NLP datasets, human factors in NLP, benchmarking

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.

Paper Type: Long

Research Area: Resources and Evaluation

Research Area Keywords: corpus creation, NLP datasets, human factors in NLP, benchmarking

Contribution Types: Data resources, Data analysis

Languages Studied: English

Submission Number: 3031