<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="wang-etal-2025-inducing">
    <titleInfo>
        <title>Inducing Argument Facets for Faithful Opinion Summarization</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Jian</namePart>
        <namePart type="family">Wang</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Yanjie</namePart>
        <namePart type="family">Liang</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Yuqing</namePart>
        <namePart type="family">Sun</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Bin</namePart>
        <namePart type="family">Gong</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2025-11</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Findings of the Association for Computational Linguistics: EMNLP 2025</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Christos</namePart>
            <namePart type="family">Christodoulopoulos</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Tanmoy</namePart>
            <namePart type="family">Chakraborty</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Carolyn</namePart>
            <namePart type="family">Rose</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Violet</namePart>
            <namePart type="family">Peng</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Suzhou, China</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
        <identifier type="isbn">979-8-89176-335-7</identifier>
    </relatedItem>
    <abstract>Faithful opinion summarization task refers to generating a summary for a set of documents that covers the majority and minority opinions in documents. Inspired by the cognitive science that argument facet is the focus of an opinion, we propose the facets-guided opinion summarization method (FacSum). By inducing the facets, we partition the documents into multiple facet-specific sets. Then key phrases are extracted as the representatives of each set and the number of facets is used for constraining the length of summary, both of which are used to guide large language models (LLMs) to cover different argument facets of opinions while keeping the summary concise. We perform experiments on two representative datasets and the results show that our method outperforms the state-of-the-art (SOTA) methods and multiple LLMs. The ablation studies indicate that the introduced facets contribute to improving model performance by enabling the coverage of minority opinions while preserving the majority ones. The results based on different LLMs demonstrate that our method can improve the performance of LLMs with varying model sizes. We apply FacSum to the summarization of professional paper reviews, and the results confirm its effectiveness in specialty domains as well.</abstract>
    <identifier type="citekey">wang-etal-2025-inducing</identifier>
    <location>
        <url>https://aclanthology.org/2025.findings-emnlp.876/</url>
    </location>
    <part>
        <date>2025-11</date>
        <extent unit="page">
            <start>16153</start>
            <end>16166</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Inducing Argument Facets for Faithful Opinion Summarization
%A Wang, Jian
%A Liang, Yanjie
%A Sun, Yuqing
%A Gong, Bin
%Y Christodoulopoulos, Christos
%Y Chakraborty, Tanmoy
%Y Rose, Carolyn
%Y Peng, Violet
%S Findings of the Association for Computational Linguistics: EMNLP 2025
%D 2025
%8 November
%I Association for Computational Linguistics
%C Suzhou, China
%@ 979-8-89176-335-7
%F wang-etal-2025-inducing
%X Faithful opinion summarization task refers to generating a summary for a set of documents that covers the majority and minority opinions in documents. Inspired by the cognitive science that argument facet is the focus of an opinion, we propose the facets-guided opinion summarization method (FacSum). By inducing the facets, we partition the documents into multiple facet-specific sets. Then key phrases are extracted as the representatives of each set and the number of facets is used for constraining the length of summary, both of which are used to guide large language models (LLMs) to cover different argument facets of opinions while keeping the summary concise. We perform experiments on two representative datasets and the results show that our method outperforms the state-of-the-art (SOTA) methods and multiple LLMs. The ablation studies indicate that the introduced facets contribute to improving model performance by enabling the coverage of minority opinions while preserving the majority ones. The results based on different LLMs demonstrate that our method can improve the performance of LLMs with varying model sizes. We apply FacSum to the summarization of professional paper reviews, and the results confirm its effectiveness in specialty domains as well.
%U https://aclanthology.org/2025.findings-emnlp.876/
%P 16153-16166

Markdown (Informal)

[Inducing Argument Facets for Faithful Opinion Summarization](https://aclanthology.org/2025.findings-emnlp.876/) (Wang et al., Findings 2025)

• Inducing Argument Facets for Faithful Opinion Summarization (Wang et al., Findings 2025)

ACL

• Jian Wang, Yanjie Liang, Yuqing Sun, and Bin Gong. 2025. Inducing Argument Facets for Faithful Opinion Summarization. In Findings of the Association for Computational Linguistics: EMNLP 2025, pages 16153–16166, Suzhou, China. Association for Computational Linguistics.