Cross-Document Event-Keyed Summarization
William Walden, Pavlo Kuchmiichuk, Alexander Martin, Chihsheng Jin, Angela Cao, Claire Sun, Curisia Allen, Aaron White
Correct Metadata for
Abstract
Event-keyed summarization (EKS) requires summarizing a specific event described in a document given the document text and an event representation extracted from it. In this work, we extend EKS to the cross-document setting (CDEKS), in which summaries must synthesize information from accounts of the same event as given by multiple sources. We introduce **SEAMuS** (**S**ummaries of **E**vents **A**cross **Mu**ltiple **S**ources), a high-quality dataset for CDEKS based on an expert reannotation of the FAMuS dataset for cross-document argument extraction. We present a suite of baselines on SEAMuS—covering both smaller, fine-tuned models, as well as zero- and few-shot prompted LLMs—along with detailed ablations and a human evaluation study, showing SEAMuS to be a valuable benchmark for this new task.- Anthology ID:
- 2025.xllm-1.19
- Volume:
- Proceedings of the 1st Joint Workshop on Large Language Models and Structure Modeling (XLLM 2025)
- Month:
- August
- Year:
- 2025
- Address:
- Vienna, Austria
- Editors:
- Hao Fei, Kewei Tu, Yuhui Zhang, Xiang Hu, Wenjuan Han, Zixia Jia, Zilong Zheng, Yixin Cao, Meishan Zhang, Wei Lu, N. Siddharth, Lilja Øvrelid, Nianwen Xue, Yue Zhang
- Venues:
- XLLM | WS
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 218–241
- Language:
- URL:
- https://aclanthology.org/2025.xllm-1.19/
- DOI:
- 10.18653/v1/2025.xllm-1.19
- Bibkey:
- Cite (ACL):
- William Walden, Pavlo Kuchmiichuk, Alexander Martin, Chihsheng Jin, Angela Cao, Claire Sun, Curisia Allen, and Aaron White. 2025. Cross-Document Event-Keyed Summarization. In Proceedings of the 1st Joint Workshop on Large Language Models and Structure Modeling (XLLM 2025), pages 218–241, Vienna, Austria. Association for Computational Linguistics.
- Cite (Informal):
- Cross-Document Event-Keyed Summarization (Walden et al., XLLM 2025)
- Copy Citation:
- PDF:
- https://aclanthology.org/2025.xllm-1.19.pdf
Export citation
@inproceedings{walden-etal-2025-cross,
title = "Cross-Document Event-Keyed Summarization",
author = "Walden, William and
Kuchmiichuk, Pavlo and
Martin, Alexander and
Jin, Chihsheng and
Cao, Angela and
Sun, Claire and
Allen, Curisia and
White, Aaron",
editor = "Fei, Hao and
Tu, Kewei and
Zhang, Yuhui and
Hu, Xiang and
Han, Wenjuan and
Jia, Zixia and
Zheng, Zilong and
Cao, Yixin and
Zhang, Meishan and
Lu, Wei and
Siddharth, N. and
{\O}vrelid, Lilja and
Xue, Nianwen and
Zhang, Yue",
booktitle = "Proceedings of the 1st Joint Workshop on Large Language Models and Structure Modeling (XLLM 2025)",
month = aug,
year = "2025",
address = "Vienna, Austria",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.xllm-1.19/",
doi = "10.18653/v1/2025.xllm-1.19",
pages = "218--241",
ISBN = "979-8-89176-286-2",
abstract = "Event-keyed summarization (EKS) requires summarizing a specific event described in a document given the document text and an event representation extracted from it. In this work, we extend EKS to the cross-document setting (CDEKS), in which summaries must synthesize information from accounts of the same event as given by multiple sources. We introduce **SEAMuS** (**S**ummaries of **E**vents **A**cross **Mu**ltiple **S**ources), a high-quality dataset for CDEKS based on an expert reannotation of the FAMuS dataset for cross-document argument extraction. We present a suite of baselines on SEAMuS{---}covering both smaller, fine-tuned models, as well as zero- and few-shot prompted LLMs{---}along with detailed ablations and a human evaluation study, showing SEAMuS to be a valuable benchmark for this new task."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="walden-etal-2025-cross">
<titleInfo>
<title>Cross-Document Event-Keyed Summarization</title>
</titleInfo>
<name type="personal">
<namePart type="given">William</namePart>
<namePart type="family">Walden</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pavlo</namePart>
<namePart type="family">Kuchmiichuk</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alexander</namePart>
<namePart type="family">Martin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chihsheng</namePart>
<namePart type="family">Jin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Angela</namePart>
<namePart type="family">Cao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Claire</namePart>
<namePart type="family">Sun</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Curisia</namePart>
<namePart type="family">Allen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Aaron</namePart>
<namePart type="family">White</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-08</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 1st Joint Workshop on Large Language Models and Structure Modeling (XLLM 2025)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Hao</namePart>
<namePart type="family">Fei</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kewei</namePart>
<namePart type="family">Tu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yuhui</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xiang</namePart>
<namePart type="family">Hu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wenjuan</namePart>
<namePart type="family">Han</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zixia</namePart>
<namePart type="family">Jia</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zilong</namePart>
<namePart type="family">Zheng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yixin</namePart>
<namePart type="family">Cao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Meishan</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wei</namePart>
<namePart type="family">Lu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">N</namePart>
<namePart type="family">Siddharth</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lilja</namePart>
<namePart type="family">Øvrelid</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nianwen</namePart>
<namePart type="family">Xue</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yue</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Vienna, Austria</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-286-2</identifier>
</relatedItem>
<abstract>Event-keyed summarization (EKS) requires summarizing a specific event described in a document given the document text and an event representation extracted from it. In this work, we extend EKS to the cross-document setting (CDEKS), in which summaries must synthesize information from accounts of the same event as given by multiple sources. We introduce **SEAMuS** (**S**ummaries of **E**vents **A**cross **Mu**ltiple **S**ources), a high-quality dataset for CDEKS based on an expert reannotation of the FAMuS dataset for cross-document argument extraction. We present a suite of baselines on SEAMuS—covering both smaller, fine-tuned models, as well as zero- and few-shot prompted LLMs—along with detailed ablations and a human evaluation study, showing SEAMuS to be a valuable benchmark for this new task.</abstract>
<identifier type="citekey">walden-etal-2025-cross</identifier>
<identifier type="doi">10.18653/v1/2025.xllm-1.19</identifier>
<location>
<url>https://aclanthology.org/2025.xllm-1.19/</url>
</location>
<part>
<date>2025-08</date>
<extent unit="page">
<start>218</start>
<end>241</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings %T Cross-Document Event-Keyed Summarization %A Walden, William %A Kuchmiichuk, Pavlo %A Martin, Alexander %A Jin, Chihsheng %A Cao, Angela %A Sun, Claire %A Allen, Curisia %A White, Aaron %Y Fei, Hao %Y Tu, Kewei %Y Zhang, Yuhui %Y Hu, Xiang %Y Han, Wenjuan %Y Jia, Zixia %Y Zheng, Zilong %Y Cao, Yixin %Y Zhang, Meishan %Y Lu, Wei %Y Siddharth, N. %Y Øvrelid, Lilja %Y Xue, Nianwen %Y Zhang, Yue %S Proceedings of the 1st Joint Workshop on Large Language Models and Structure Modeling (XLLM 2025) %D 2025 %8 August %I Association for Computational Linguistics %C Vienna, Austria %@ 979-8-89176-286-2 %F walden-etal-2025-cross %X Event-keyed summarization (EKS) requires summarizing a specific event described in a document given the document text and an event representation extracted from it. In this work, we extend EKS to the cross-document setting (CDEKS), in which summaries must synthesize information from accounts of the same event as given by multiple sources. We introduce **SEAMuS** (**S**ummaries of **E**vents **A**cross **Mu**ltiple **S**ources), a high-quality dataset for CDEKS based on an expert reannotation of the FAMuS dataset for cross-document argument extraction. We present a suite of baselines on SEAMuS—covering both smaller, fine-tuned models, as well as zero- and few-shot prompted LLMs—along with detailed ablations and a human evaluation study, showing SEAMuS to be a valuable benchmark for this new task. %R 10.18653/v1/2025.xllm-1.19 %U https://aclanthology.org/2025.xllm-1.19/ %U https://doi.org/10.18653/v1/2025.xllm-1.19 %P 218-241
Markdown (Informal)
[Cross-Document Event-Keyed Summarization](https://aclanthology.org/2025.xllm-1.19/) (Walden et al., XLLM 2025)
- Cross-Document Event-Keyed Summarization (Walden et al., XLLM 2025)
ACL
- William Walden, Pavlo Kuchmiichuk, Alexander Martin, Chihsheng Jin, Angela Cao, Claire Sun, Curisia Allen, and Aaron White. 2025. Cross-Document Event-Keyed Summarization. In Proceedings of the 1st Joint Workshop on Large Language Models and Structure Modeling (XLLM 2025), pages 218–241, Vienna, Austria. Association for Computational Linguistics.