@inproceedings{dela-cruz-etal-2026-beyond,
title = "Beyond Consensus: Diagnosing Coverage, Majority Bias, and Grounding Equity in High-Stakes Multi-Document Diversity Summarization",
author = "dela Cruz, Jane Arleth and
Hendrickx, Iris and
Larson, Martha",
editor = "Zhang, Yue and
Xu, Ruifeng and
Purwarianti, Ayu and
Rong, Tong and
Suzuki, Jun",
booktitle = "Findings of the {A}ssociation for {C}omputational {L}inguistics: {IJCNLP}-{AACL} 2026",
month = nov,
year = "2026",
address = "Hengqin, China",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.findings-aacl.246/",
pages = "4831--4845",
ISBN = "979-8-89176-444-6",
abstract = "Multi-document diversity summarization (MDDS) in high-stakes domains such as crisis response demands fundamentally different capabilities than consensus-based summarization. While standard summarization focus on fluency and faithfulness, high-stakes tasks would also require: maximizing coverage of divergent information, identifying unique information clusters, and providing verifiable citations to source documents. Existing evaluation frameworks fail to capture these task-specific requirements. Our study introduces a comprehensive evaluation framework for high-stakes MDDS, validated on a multi-source crisis dataset that we developed covering ten crisis events. We propose novel metrics, Comprehensive Coverage Score, Frequency-Salience Correlation, and Citation-Frequency Correlation, to diagnose critical failure modes in six off-the-shelf large language models (LLMs). Our results allow us to identify three critical failure modes of LLMs: (1) a consensus trap in coverage: where models capture high-level information clusters, but miss specific, actionable details needed for decision-making; (2) majority bias, where more frequent information are prioritized over rare but important ones and; (3) a verifiability gap, where citations of rare claims are less reliable"
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="dela-cruz-etal-2026-beyond">
<titleInfo>
<title>Beyond Consensus: Diagnosing Coverage, Majority Bias, and Grounding Equity in High-Stakes Multi-Document Diversity Summarization</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jane</namePart>
<namePart type="given">Arleth</namePart>
<namePart type="family">dela Cruz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Iris</namePart>
<namePart type="family">Hendrickx</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Martha</namePart>
<namePart type="family">Larson</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>Findings of the Association for Computational Linguistics: IJCNLP-AACL 2026</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">979-8-89176-444-6</identifier>
</relatedItem>
<abstract>Multi-document diversity summarization (MDDS) in high-stakes domains such as crisis response demands fundamentally different capabilities than consensus-based summarization. While standard summarization focus on fluency and faithfulness, high-stakes tasks would also require: maximizing coverage of divergent information, identifying unique information clusters, and providing verifiable citations to source documents. Existing evaluation frameworks fail to capture these task-specific requirements. Our study introduces a comprehensive evaluation framework for high-stakes MDDS, validated on a multi-source crisis dataset that we developed covering ten crisis events. We propose novel metrics, Comprehensive Coverage Score, Frequency-Salience Correlation, and Citation-Frequency Correlation, to diagnose critical failure modes in six off-the-shelf large language models (LLMs). Our results allow us to identify three critical failure modes of LLMs: (1) a consensus trap in coverage: where models capture high-level information clusters, but miss specific, actionable details needed for decision-making; (2) majority bias, where more frequent information are prioritized over rare but important ones and; (3) a verifiability gap, where citations of rare claims are less reliable</abstract>
<identifier type="citekey">dela-cruz-etal-2026-beyond</identifier>
<location>
<url>https://aclanthology.org/2026.findings-aacl.246/</url>
</location>
<part>
<date>2026-11</date>
<extent unit="page">
<start>4831</start>
<end>4845</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Beyond Consensus: Diagnosing Coverage, Majority Bias, and Grounding Equity in High-Stakes Multi-Document Diversity Summarization
%A dela Cruz, Jane Arleth
%A Hendrickx, Iris
%A Larson, Martha
%Y Zhang, Yue
%Y Xu, Ruifeng
%Y Purwarianti, Ayu
%Y Rong, Tong
%Y Suzuki, Jun
%S Findings of the Association for Computational Linguistics: IJCNLP-AACL 2026
%D 2026
%8 November
%I Association for Computational Linguistics
%C Hengqin, China
%@ 979-8-89176-444-6
%F dela-cruz-etal-2026-beyond
%X Multi-document diversity summarization (MDDS) in high-stakes domains such as crisis response demands fundamentally different capabilities than consensus-based summarization. While standard summarization focus on fluency and faithfulness, high-stakes tasks would also require: maximizing coverage of divergent information, identifying unique information clusters, and providing verifiable citations to source documents. Existing evaluation frameworks fail to capture these task-specific requirements. Our study introduces a comprehensive evaluation framework for high-stakes MDDS, validated on a multi-source crisis dataset that we developed covering ten crisis events. We propose novel metrics, Comprehensive Coverage Score, Frequency-Salience Correlation, and Citation-Frequency Correlation, to diagnose critical failure modes in six off-the-shelf large language models (LLMs). Our results allow us to identify three critical failure modes of LLMs: (1) a consensus trap in coverage: where models capture high-level information clusters, but miss specific, actionable details needed for decision-making; (2) majority bias, where more frequent information are prioritized over rare but important ones and; (3) a verifiability gap, where citations of rare claims are less reliable
%U https://aclanthology.org/2026.findings-aacl.246/
%P 4831-4845
Markdown (Informal)
[Beyond Consensus: Diagnosing Coverage, Majority Bias, and Grounding Equity in High-Stakes Multi-Document Diversity Summarization](https://aclanthology.org/2026.findings-aacl.246/) (dela Cruz et al., Findings 2026)
ACL