<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="liu-etal-2025-explanatory">
    <titleInfo>
        <title>Explanatory Summarization with Discourse-Driven Planning</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Dongqi</namePart>
        <namePart type="family">Liu</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Xi</namePart>
        <namePart type="family">Yu</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Vera</namePart>
        <namePart type="family">Demberg</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Mirella</namePart>
        <namePart type="family">Lapata</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2025</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <genre authority="bibutilsgt">journal article</genre>
    <relatedItem type="host">
        <titleInfo>
            <title>Transactions of the Association for Computational Linguistics</title>
        </titleInfo>
        <originInfo>
            <issuance>continuing</issuance>
            <publisher>MIT Press</publisher>
            <place>
                <placeTerm type="text">Cambridge, MA</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">periodical</genre>
        <genre authority="bibutilsgt">academic journal</genre>
    </relatedItem>
    <abstract>Lay summaries for scientific documents typically include explanations to help readers grasp sophisticated concepts or arguments. However, current automatic summarization methods do not explicitly model explanations, which makes it difficult to align the proportion of explanatory content with human-written summaries. In this paper, we present a plan-based approach that leverages discourse frameworks to organize summary generation and guide explanatory sentences by prompting responses to the plan. Specifically, we propose two discourse-driven planning strategies, where the plan is conditioned as part of the input or part of the output prefix, respectively. Empirical experiments on three lay summarization datasets show that our approach outperforms existing state-of-the-art methods in terms of summary quality, and it enhances model robustness, controllability, and mitigates hallucination. The project information is available at https://dongqi.me/projects/ExpSum.</abstract>
    <identifier type="citekey">liu-etal-2025-explanatory</identifier>
    <identifier type="doi">10.1162/tacl.a.30</identifier>
    <location>
        <url>https://aclanthology.org/2025.tacl-1.53/</url>
    </location>
    <part>
        <date>2025</date>
        <detail type="volume"><number>13</number></detail>
        <extent unit="page">
            <start>1146</start>
            <end>1170</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Journal Article
%T Explanatory Summarization with Discourse-Driven Planning
%A Liu, Dongqi
%A Yu, Xi
%A Demberg, Vera
%A Lapata, Mirella
%J Transactions of the Association for Computational Linguistics
%D 2025
%V 13
%I MIT Press
%C Cambridge, MA
%F liu-etal-2025-explanatory
%X Lay summaries for scientific documents typically include explanations to help readers grasp sophisticated concepts or arguments. However, current automatic summarization methods do not explicitly model explanations, which makes it difficult to align the proportion of explanatory content with human-written summaries. In this paper, we present a plan-based approach that leverages discourse frameworks to organize summary generation and guide explanatory sentences by prompting responses to the plan. Specifically, we propose two discourse-driven planning strategies, where the plan is conditioned as part of the input or part of the output prefix, respectively. Empirical experiments on three lay summarization datasets show that our approach outperforms existing state-of-the-art methods in terms of summary quality, and it enhances model robustness, controllability, and mitigates hallucination. The project information is available at https://dongqi.me/projects/ExpSum.
%R 10.1162/tacl.a.30
%U https://aclanthology.org/2025.tacl-1.53/
%U https://doi.org/10.1162/tacl.a.30
%P 1146-1170

Markdown (Informal)

[Explanatory Summarization with Discourse-Driven Planning](https://aclanthology.org/2025.tacl-1.53/) (Liu et al., TACL 2025)

• Explanatory Summarization with Discourse-Driven Planning (Liu et al., TACL 2025)

ACL

• Dongqi Liu, Xi Yu, Vera Demberg, and Mirella Lapata. 2025. Explanatory Summarization with Discourse-Driven Planning. Transactions of the Association for Computational Linguistics, 13:1146–1170.