@inproceedings{yuan-zhang-2025-domainsum,
title = "{D}omain{S}um: A Hierarchical Benchmark for Fine-Grained Domain Shift in Abstractive Text Summarization",
author = "Yuan, Haohan and
Zhang, Haopeng",
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.118/",
doi = "10.18653/v1/2025.findings-naacl.118",
pages = "2219--2231",
ISBN = "979-8-89176-195-7",
abstract = "Most research on abstractive summarization focuses on single-domain applications, often neglecting how domain shifts between documents affect performance and the generalization ability of summarization models. To address this issue, we introduce DomainSum, a hierarchical benchmark designed to capture fine-grained domain shifts in abstractive summarization. We categorize these shifts into three levels: genre, style, and topic, and demonstrate through comprehensive benchmark analysis that they follow a hierarchical structure. Furthermore, we evaluate the domain generalization capabilities of commonly used pre-trained language models (PLMs) and large language models (LLMs) in both in-domain and cross-domain settings. Our benchmark and source code are released at https://github.com/hpzhang94/DomainSum."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="yuan-zhang-2025-domainsum">
<titleInfo>
<title>DomainSum: A Hierarchical Benchmark for Fine-Grained Domain Shift in Abstractive Text Summarization</title>
</titleInfo>
<name type="personal">
<namePart type="given">Haohan</namePart>
<namePart type="family">Yuan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Haopeng</namePart>
<namePart type="family">Zhang</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>Most research on abstractive summarization focuses on single-domain applications, often neglecting how domain shifts between documents affect performance and the generalization ability of summarization models. To address this issue, we introduce DomainSum, a hierarchical benchmark designed to capture fine-grained domain shifts in abstractive summarization. We categorize these shifts into three levels: genre, style, and topic, and demonstrate through comprehensive benchmark analysis that they follow a hierarchical structure. Furthermore, we evaluate the domain generalization capabilities of commonly used pre-trained language models (PLMs) and large language models (LLMs) in both in-domain and cross-domain settings. Our benchmark and source code are released at https://github.com/hpzhang94/DomainSum.</abstract>
<identifier type="citekey">yuan-zhang-2025-domainsum</identifier>
<identifier type="doi">10.18653/v1/2025.findings-naacl.118</identifier>
<location>
<url>https://aclanthology.org/2025.findings-naacl.118/</url>
</location>
<part>
<date>2025-04</date>
<extent unit="page">
<start>2219</start>
<end>2231</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T DomainSum: A Hierarchical Benchmark for Fine-Grained Domain Shift in Abstractive Text Summarization
%A Yuan, Haohan
%A Zhang, Haopeng
%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 yuan-zhang-2025-domainsum
%X Most research on abstractive summarization focuses on single-domain applications, often neglecting how domain shifts between documents affect performance and the generalization ability of summarization models. To address this issue, we introduce DomainSum, a hierarchical benchmark designed to capture fine-grained domain shifts in abstractive summarization. We categorize these shifts into three levels: genre, style, and topic, and demonstrate through comprehensive benchmark analysis that they follow a hierarchical structure. Furthermore, we evaluate the domain generalization capabilities of commonly used pre-trained language models (PLMs) and large language models (LLMs) in both in-domain and cross-domain settings. Our benchmark and source code are released at https://github.com/hpzhang94/DomainSum.
%R 10.18653/v1/2025.findings-naacl.118
%U https://aclanthology.org/2025.findings-naacl.118/
%U https://doi.org/10.18653/v1/2025.findings-naacl.118
%P 2219-2231
Markdown (Informal)
[DomainSum: A Hierarchical Benchmark for Fine-Grained Domain Shift in Abstractive Text Summarization](https://aclanthology.org/2025.findings-naacl.118/) (Yuan & Zhang, Findings 2025)
ACL