@inproceedings{zhang-etal-2025-massw,
title = "{MASSW}: A New Dataset and Benchmark Tasks for {AI}-Assisted Scientific Workflows",
author = "Zhang, Xingjian and
Xie, Yutong and
Huang, Jin and
Ma, Jinge and
Pan, Zhaoying and
Liu, Qijia and
Xiong, Ziyang and
Ergen, Tolga and
Shim, Dongsub and
Lee, Honglak and
Mei, Qiaozhu",
editor = "Chiruzzo, Luis and
Ritter, Alan and
Wang, Lu",
booktitle = "Findings of the Association for Computational Linguistics: NAACL 2025",
month = apr,
year = "2025",
address = "Albuquerque, New Mexico",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.findings-naacl.127/",
pages = "2373--2394",
ISBN = "979-8-89176-195-7",
abstract = "Scientific innovation relies on detailed workflows, which include critical steps such as contextualizing literature, generating ideas, validating ideas, interpreting results, and planning new research. Scientific publications that document these workflows are extensive and unstructured, making it difficult to effectively navigate and explore the space of scientific innovation. To meet this challenge, we introduce **MASSW**, a comprehensive dataset of **M**ulti-**A**spect **S**ummarization of **S**cientific **W**orkflows. MASSW includes more than 152,000 peer-reviewed publications from 17 leading computer science conferences spanning the past 50 years. Using Large Language Models (LLMs), we automatically extract five core aspects from these publications {--} *context, key idea, method, outcome*, and *projected impact* {--} which correspond to five key steps in a research workflow. We show that these LLM-extract summaries have a comparable quality to human annotations, and they facilitate a variety of downstream tasks, corresponding to different types of predictions and recommendations along the scientific workflow. Overall, MASSW demonstrates decent utility as a pre-computed and trustful resource for the AI4Science community to create and benchmark a wide-range of new AI methods for optimizing scientific workflows and fostering scientific innovation. Our code and datasets are made available anonymously: [link](https://osf.io/7ygrq/?view{\_}only=3d8261a0ea09489fa67ece2c68235afa)."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zhang-etal-2025-massw">
<titleInfo>
<title>MASSW: A New Dataset and Benchmark Tasks for AI-Assisted Scientific Workflows</title>
</titleInfo>
<name type="personal">
<namePart type="given">Xingjian</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yutong</namePart>
<namePart type="family">Xie</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jin</namePart>
<namePart type="family">Huang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jinge</namePart>
<namePart type="family">Ma</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhaoying</namePart>
<namePart type="family">Pan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Qijia</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ziyang</namePart>
<namePart type="family">Xiong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tolga</namePart>
<namePart type="family">Ergen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dongsub</namePart>
<namePart type="family">Shim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Honglak</namePart>
<namePart type="family">Lee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Qiaozhu</namePart>
<namePart type="family">Mei</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-04</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: NAACL 2025</title>
</titleInfo>
<name type="personal">
<namePart type="given">Luis</namePart>
<namePart type="family">Chiruzzo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alan</namePart>
<namePart type="family">Ritter</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lu</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">Albuquerque, New Mexico</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-195-7</identifier>
</relatedItem>
<abstract>Scientific innovation relies on detailed workflows, which include critical steps such as contextualizing literature, generating ideas, validating ideas, interpreting results, and planning new research. Scientific publications that document these workflows are extensive and unstructured, making it difficult to effectively navigate and explore the space of scientific innovation. To meet this challenge, we introduce **MASSW**, a comprehensive dataset of **M**ulti-**A**spect **S**ummarization of **S**cientific **W**orkflows. MASSW includes more than 152,000 peer-reviewed publications from 17 leading computer science conferences spanning the past 50 years. Using Large Language Models (LLMs), we automatically extract five core aspects from these publications – *context, key idea, method, outcome*, and *projected impact* – which correspond to five key steps in a research workflow. We show that these LLM-extract summaries have a comparable quality to human annotations, and they facilitate a variety of downstream tasks, corresponding to different types of predictions and recommendations along the scientific workflow. Overall, MASSW demonstrates decent utility as a pre-computed and trustful resource for the AI4Science community to create and benchmark a wide-range of new AI methods for optimizing scientific workflows and fostering scientific innovation. Our code and datasets are made available anonymously: [link](https://osf.io/7ygrq/?view_only=3d8261a0ea09489fa67ece2c68235afa).</abstract>
<identifier type="citekey">zhang-etal-2025-massw</identifier>
<location>
<url>https://aclanthology.org/2025.findings-naacl.127/</url>
</location>
<part>
<date>2025-04</date>
<extent unit="page">
<start>2373</start>
<end>2394</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T MASSW: A New Dataset and Benchmark Tasks for AI-Assisted Scientific Workflows
%A Zhang, Xingjian
%A Xie, Yutong
%A Huang, Jin
%A Ma, Jinge
%A Pan, Zhaoying
%A Liu, Qijia
%A Xiong, Ziyang
%A Ergen, Tolga
%A Shim, Dongsub
%A Lee, Honglak
%A Mei, Qiaozhu
%Y Chiruzzo, Luis
%Y Ritter, Alan
%Y Wang, Lu
%S Findings of the Association for Computational Linguistics: NAACL 2025
%D 2025
%8 April
%I Association for Computational Linguistics
%C Albuquerque, New Mexico
%@ 979-8-89176-195-7
%F zhang-etal-2025-massw
%X Scientific innovation relies on detailed workflows, which include critical steps such as contextualizing literature, generating ideas, validating ideas, interpreting results, and planning new research. Scientific publications that document these workflows are extensive and unstructured, making it difficult to effectively navigate and explore the space of scientific innovation. To meet this challenge, we introduce **MASSW**, a comprehensive dataset of **M**ulti-**A**spect **S**ummarization of **S**cientific **W**orkflows. MASSW includes more than 152,000 peer-reviewed publications from 17 leading computer science conferences spanning the past 50 years. Using Large Language Models (LLMs), we automatically extract five core aspects from these publications – *context, key idea, method, outcome*, and *projected impact* – which correspond to five key steps in a research workflow. We show that these LLM-extract summaries have a comparable quality to human annotations, and they facilitate a variety of downstream tasks, corresponding to different types of predictions and recommendations along the scientific workflow. Overall, MASSW demonstrates decent utility as a pre-computed and trustful resource for the AI4Science community to create and benchmark a wide-range of new AI methods for optimizing scientific workflows and fostering scientific innovation. Our code and datasets are made available anonymously: [link](https://osf.io/7ygrq/?view_only=3d8261a0ea09489fa67ece2c68235afa).
%U https://aclanthology.org/2025.findings-naacl.127/
%P 2373-2394
Markdown (Informal)
[MASSW: A New Dataset and Benchmark Tasks for AI-Assisted Scientific Workflows](https://aclanthology.org/2025.findings-naacl.127/) (Zhang et al., Findings 2025)
ACL
- Xingjian Zhang, Yutong Xie, Jin Huang, Jinge Ma, Zhaoying Pan, Qijia Liu, Ziyang Xiong, Tolga Ergen, Dongsub Shim, Honglak Lee, and Qiaozhu Mei. 2025. MASSW: A New Dataset and Benchmark Tasks for AI-Assisted Scientific Workflows. In Findings of the Association for Computational Linguistics: NAACL 2025, pages 2373–2394, Albuquerque, New Mexico. Association for Computational Linguistics.