@inproceedings{li-chaturvedi-2026-comparative,
title = "Comparative Personalization for Multi-document Summarization",
author = "Li, Haoyuan and
Chaturvedi, Snigdha",
editor = "Zhang, Yue and
Xu, Ruifeng and
Purwarianti, Ayu and
Rong, Tong and
Suzuki, Jun",
booktitle = "Proceedings of the 15th International Joint Conference on Natural Language Processing and the 5th Conference of the {A}sia-Pacific Chapter of the {A}ssociation for {C}omputational {L}inguistics (Volume 1: Long Papers)",
month = nov,
year = "2026",
address = "Hengqin, China",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.aacl-long.47/",
pages = "966--985",
ISBN = "979-8-89176-439-2",
abstract = "Personalized multi-document summarization (MDS) is essential for meeting individual user preferences of writing style and content focus for summaries. In this paper, we propose that for effective personalization, it is important to identify fine-grained differences between users' preferences by comparing preferences of different users. Motivated by this, we propose ComPSum, a personalized MDS framework. It first generates a structured analysis of a user by comparison between users. The generated structured analysis is then used to guide the generation of personalized summaries. To evaluate ComPSum, we propose AuthorMap, a fine-grained reference-free evaluation framework for personalized MDS. It evaluates the personalization of a system based on the authorship attribution between two personalized summaries generated for different users. For robust evaluation of personalized MDS, we construct PerMSum, a personalized MDS dataset in the review and news domain. We evaluate the performance of ComPSum, showing that it outperforms strong baselines. The code is available at https://github.com/leehaoyuan/comparative{\_}personalize{\_}sum."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="li-chaturvedi-2026-comparative">
<titleInfo>
<title>Comparative Personalization for Multi-document Summarization</title>
</titleInfo>
<name type="personal">
<namePart type="given">Haoyuan</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Snigdha</namePart>
<namePart type="family">Chaturvedi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 15th International Joint Conference on Natural Language Processing and the 5th Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics (Volume 1: Long Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yue</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ruifeng</namePart>
<namePart type="family">Xu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ayu</namePart>
<namePart type="family">Purwarianti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tong</namePart>
<namePart type="family">Rong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jun</namePart>
<namePart type="family">Suzuki</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Hengqin, China</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-439-2</identifier>
</relatedItem>
<abstract>Personalized multi-document summarization (MDS) is essential for meeting individual user preferences of writing style and content focus for summaries. In this paper, we propose that for effective personalization, it is important to identify fine-grained differences between users’ preferences by comparing preferences of different users. Motivated by this, we propose ComPSum, a personalized MDS framework. It first generates a structured analysis of a user by comparison between users. The generated structured analysis is then used to guide the generation of personalized summaries. To evaluate ComPSum, we propose AuthorMap, a fine-grained reference-free evaluation framework for personalized MDS. It evaluates the personalization of a system based on the authorship attribution between two personalized summaries generated for different users. For robust evaluation of personalized MDS, we construct PerMSum, a personalized MDS dataset in the review and news domain. We evaluate the performance of ComPSum, showing that it outperforms strong baselines. The code is available at https://github.com/leehaoyuan/comparative_personalize_sum.</abstract>
<identifier type="citekey">li-chaturvedi-2026-comparative</identifier>
<location>
<url>https://aclanthology.org/2026.aacl-long.47/</url>
</location>
<part>
<date>2026-11</date>
<extent unit="page">
<start>966</start>
<end>985</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Comparative Personalization for Multi-document Summarization
%A Li, Haoyuan
%A Chaturvedi, Snigdha
%Y Zhang, Yue
%Y Xu, Ruifeng
%Y Purwarianti, Ayu
%Y Rong, Tong
%Y Suzuki, Jun
%S Proceedings of the 15th International Joint Conference on Natural Language Processing and the 5th Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics (Volume 1: Long Papers)
%D 2026
%8 November
%I Association for Computational Linguistics
%C Hengqin, China
%@ 979-8-89176-439-2
%F li-chaturvedi-2026-comparative
%X Personalized multi-document summarization (MDS) is essential for meeting individual user preferences of writing style and content focus for summaries. In this paper, we propose that for effective personalization, it is important to identify fine-grained differences between users’ preferences by comparing preferences of different users. Motivated by this, we propose ComPSum, a personalized MDS framework. It first generates a structured analysis of a user by comparison between users. The generated structured analysis is then used to guide the generation of personalized summaries. To evaluate ComPSum, we propose AuthorMap, a fine-grained reference-free evaluation framework for personalized MDS. It evaluates the personalization of a system based on the authorship attribution between two personalized summaries generated for different users. For robust evaluation of personalized MDS, we construct PerMSum, a personalized MDS dataset in the review and news domain. We evaluate the performance of ComPSum, showing that it outperforms strong baselines. The code is available at https://github.com/leehaoyuan/comparative_personalize_sum.
%U https://aclanthology.org/2026.aacl-long.47/
%P 966-985
Markdown (Informal)
[Comparative Personalization for Multi-document Summarization](https://aclanthology.org/2026.aacl-long.47/) (Li & Chaturvedi, AACL-IJCNLP 2026)
ACL
- Haoyuan Li and Snigdha Chaturvedi. 2026. Comparative Personalization for Multi-document Summarization. In Proceedings of the 15th International Joint Conference on Natural Language Processing and the 5th Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics (Volume 1: Long Papers), pages 966–985, Hengqin, China. Association for Computational Linguistics.