<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="trainin-abend-2025-t5score">
    <titleInfo>
        <title>T⁵Score: A Methodology for Automatically Assessing the Quality of LLM Generated Multi-Document Topic Sets</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Itamar</namePart>
        <namePart type="family">Trainin</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Omri</namePart>
        <namePart type="family">Abend</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2025-07</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Findings of the Association for Computational Linguistics: ACL 2025</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Wanxiang</namePart>
            <namePart type="family">Che</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Joyce</namePart>
            <namePart type="family">Nabende</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Ekaterina</namePart>
            <namePart type="family">Shutova</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Mohammad</namePart>
            <namePart type="given">Taher</namePart>
            <namePart type="family">Pilehvar</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">979-8-89176-256-5</identifier>
    </relatedItem>
    <abstract>Using LLMs for Multi-Document Topic Extraction has recently gained popularity due to their apparent high-quality outputs, expressiveness, and ease of use. However, most existing evaluation practices are not designed for LLM-generated topics and result in low inter-annotator agreement scores, hindering the reliable use of LLMs for the task. To address this, we introduce T⁵Score, an evaluation methodology that decomposes the quality of a topic set into quantifiable aspects, measurable through easy-to-perform annotation tasks. This framing enables a convenient, manual or automatic, evaluation procedure resulting in a strong inter-annotator agreement score.To substantiate our methodology and claims, we perform extensive experimentation on multiple datasets and report the results.</abstract>
    <identifier type="citekey">trainin-abend-2025-t5score</identifier>
    <identifier type="doi">10.18653/v1/2025.findings-acl.1351</identifier>
    <location>
        <url>https://aclanthology.org/2025.findings-acl.1351/</url>
    </location>
    <part>
        <date>2025-07</date>
        <extent unit="page">
            <start>26347</start>
            <end>26375</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T T⁵Score: A Methodology for Automatically Assessing the Quality of LLM Generated Multi-Document Topic Sets
%A Trainin, Itamar
%A Abend, Omri
%Y Che, Wanxiang
%Y Nabende, Joyce
%Y Shutova, Ekaterina
%Y Pilehvar, Mohammad Taher
%S Findings of the Association for Computational Linguistics: ACL 2025
%D 2025
%8 July
%I Association for Computational Linguistics
%C Vienna, Austria
%@ 979-8-89176-256-5
%F trainin-abend-2025-t5score
%X Using LLMs for Multi-Document Topic Extraction has recently gained popularity due to their apparent high-quality outputs, expressiveness, and ease of use. However, most existing evaluation practices are not designed for LLM-generated topics and result in low inter-annotator agreement scores, hindering the reliable use of LLMs for the task. To address this, we introduce T⁵Score, an evaluation methodology that decomposes the quality of a topic set into quantifiable aspects, measurable through easy-to-perform annotation tasks. This framing enables a convenient, manual or automatic, evaluation procedure resulting in a strong inter-annotator agreement score.To substantiate our methodology and claims, we perform extensive experimentation on multiple datasets and report the results.
%R 10.18653/v1/2025.findings-acl.1351
%U https://aclanthology.org/2025.findings-acl.1351/
%U https://doi.org/10.18653/v1/2025.findings-acl.1351
%P 26347-26375

Markdown (Informal)

[T5Score: A Methodology for Automatically Assessing the Quality of LLM Generated Multi-Document Topic Sets](https://aclanthology.org/2025.findings-acl.1351/) (Trainin & Abend, Findings 2025)

• T5Score: A Methodology for Automatically Assessing the Quality of LLM Generated Multi-Document Topic Sets (Trainin & Abend, Findings 2025)

ACL

• Itamar Trainin and Omri Abend. 2025. T5Score: A Methodology for Automatically Assessing the Quality of LLM Generated Multi-Document Topic Sets. In Findings of the Association for Computational Linguistics: ACL 2025, pages 26347–26375, Vienna, Austria. Association for Computational Linguistics.