@inproceedings{zhang-etal-2026-datasets,
title = "Datasets for Scientific Literature Understanding: A Survey",
author = "Zhang, Yuanzhe and
Zhao, Xun and
Hu, Maodi and
Sun, Xi and
Song, Donghuan and
Zhang, Zhixiong",
editor = "Liakata, Maria and
Moreira, Viviane P. and
Zhang, Jiajun and
Jurgens, David",
booktitle = "Findings of the {A}ssociation for {C}omputational {L}inguistics: {ACL} 2026",
month = jul,
year = "2026",
address = "San Diego, California, United States",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.findings-acl.1414/",
pages = "28369--28389",
ISBN = "979-8-89176-395-1",
abstract = "Empowering machines to understand scientific literature is crucial for accelerating scientific discovery and advancing the AI for Science (AI4S) paradigm. In this paper, we present a comprehensive survey of datasets serving this domain. We propose a systematic taxonomy that organizes resources spanning structural understanding, text understanding, multimodal understanding and pre-training/instruction fine-tuning. Beyond a structured overview, we discuss the evolution of the field, elucidating how the emergence of Large Language Models (LLMs) has reshaped research priorities of dataset construction. By synthesizing existing datasets and identifying critical future directions, this work provides a roadmap for advancing intelligent scientific research systems."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zhang-etal-2026-datasets">
<titleInfo>
<title>Datasets for Scientific Literature Understanding: A Survey</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yuanzhe</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xun</namePart>
<namePart type="family">Zhao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Maodi</namePart>
<namePart type="family">Hu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xi</namePart>
<namePart type="family">Sun</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Donghuan</namePart>
<namePart type="family">Song</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhixiong</namePart>
<namePart type="family">Zhang</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>Findings of the Association for Computational Linguistics: ACL 2026</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">979-8-89176-395-1</identifier>
</relatedItem>
<abstract>Empowering machines to understand scientific literature is crucial for accelerating scientific discovery and advancing the AI for Science (AI4S) paradigm. In this paper, we present a comprehensive survey of datasets serving this domain. We propose a systematic taxonomy that organizes resources spanning structural understanding, text understanding, multimodal understanding and pre-training/instruction fine-tuning. Beyond a structured overview, we discuss the evolution of the field, elucidating how the emergence of Large Language Models (LLMs) has reshaped research priorities of dataset construction. By synthesizing existing datasets and identifying critical future directions, this work provides a roadmap for advancing intelligent scientific research systems.</abstract>
<identifier type="citekey">zhang-etal-2026-datasets</identifier>
<location>
<url>https://aclanthology.org/2026.findings-acl.1414/</url>
</location>
<part>
<date>2026-07</date>
<extent unit="page">
<start>28369</start>
<end>28389</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Datasets for Scientific Literature Understanding: A Survey
%A Zhang, Yuanzhe
%A Zhao, Xun
%A Hu, Maodi
%A Sun, Xi
%A Song, Donghuan
%A Zhang, Zhixiong
%Y Liakata, Maria
%Y Moreira, Viviane P.
%Y Zhang, Jiajun
%Y Jurgens, David
%S Findings of the Association for Computational Linguistics: ACL 2026
%D 2026
%8 July
%I Association for Computational Linguistics
%C San Diego, California, United States
%@ 979-8-89176-395-1
%F zhang-etal-2026-datasets
%X Empowering machines to understand scientific literature is crucial for accelerating scientific discovery and advancing the AI for Science (AI4S) paradigm. In this paper, we present a comprehensive survey of datasets serving this domain. We propose a systematic taxonomy that organizes resources spanning structural understanding, text understanding, multimodal understanding and pre-training/instruction fine-tuning. Beyond a structured overview, we discuss the evolution of the field, elucidating how the emergence of Large Language Models (LLMs) has reshaped research priorities of dataset construction. By synthesizing existing datasets and identifying critical future directions, this work provides a roadmap for advancing intelligent scientific research systems.
%U https://aclanthology.org/2026.findings-acl.1414/
%P 28369-28389
Markdown (Informal)
[Datasets for Scientific Literature Understanding: A Survey](https://aclanthology.org/2026.findings-acl.1414/) (Zhang et al., Findings 2026)
ACL
- Yuanzhe Zhang, Xun Zhao, Maodi Hu, Xi Sun, Donghuan Song, and Zhixiong Zhang. 2026. Datasets for Scientific Literature Understanding: A Survey. In Findings of the Association for Computational Linguistics: ACL 2026, pages 28369–28389, San Diego, California, United States. Association for Computational Linguistics.