<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="li-etal-2025-building">
    <titleInfo>
        <title>Building Data-Driven Occupation Taxonomies: A Bottom-Up Multi-Stage Approach via Semantic Clustering and Multi-Agent Collaboration</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Nan</namePart>
        <namePart type="family">Li</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Bo</namePart>
        <namePart type="family">Kang</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Tijl</namePart>
        <namePart type="family">De Bie</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>Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing: Industry Track</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Saloni</namePart>
            <namePart type="family">Potdar</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Lina</namePart>
            <namePart type="family">Rojas-Barahona</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Sebastien</namePart>
            <namePart type="family">Montella</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">979-8-89176-333-3</identifier>
    </relatedItem>
    <abstract>Creating robust occupation taxonomies, vital for applications ranging from job recommendation to labor market intelligence, is challenging.Manual curation is slow, while existing automated methods are either not adaptive to dynamic regional markets (top-down) or struggle to build coherent hierarchies from noisy data (bottom-up). We introduce CLIMB (CLusterIng-based Multi-agent taxonomy Builder), a framework that fully automates the creation of high-quality, data-driven taxonomies from raw job postings. CLIMB uses global semantic clustering to distill core occupations, then employs a reflection-based multi-agent system to iteratively build a coherent hierarchy. On three diverse, real-world datasets, we show that CLIMB produces taxonomies that are more coherent and scalable than existing methods and successfully capture unique regional characteristics. We release our code and datasets at https://github.com/aida-ugent/CLIMB.</abstract>
    <identifier type="citekey">li-etal-2025-building</identifier>
    <location>
        <url>https://aclanthology.org/2025.emnlp-industry.113/</url>
    </location>
    <part>
        <date>2025-11</date>
        <extent unit="page">
            <start>1596</start>
            <end>1614</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Building Data-Driven Occupation Taxonomies: A Bottom-Up Multi-Stage Approach via Semantic Clustering and Multi-Agent Collaboration
%A Li, Nan
%A Kang, Bo
%A De Bie, Tijl
%Y Potdar, Saloni
%Y Rojas-Barahona, Lina
%Y Montella, Sebastien
%S Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing: Industry Track
%D 2025
%8 November
%I Association for Computational Linguistics
%C Suzhou (China)
%@ 979-8-89176-333-3
%F li-etal-2025-building
%X Creating robust occupation taxonomies, vital for applications ranging from job recommendation to labor market intelligence, is challenging.Manual curation is slow, while existing automated methods are either not adaptive to dynamic regional markets (top-down) or struggle to build coherent hierarchies from noisy data (bottom-up). We introduce CLIMB (CLusterIng-based Multi-agent taxonomy Builder), a framework that fully automates the creation of high-quality, data-driven taxonomies from raw job postings. CLIMB uses global semantic clustering to distill core occupations, then employs a reflection-based multi-agent system to iteratively build a coherent hierarchy. On three diverse, real-world datasets, we show that CLIMB produces taxonomies that are more coherent and scalable than existing methods and successfully capture unique regional characteristics. We release our code and datasets at https://github.com/aida-ugent/CLIMB.
%U https://aclanthology.org/2025.emnlp-industry.113/
%P 1596-1614

Markdown (Informal)

[Building Data-Driven Occupation Taxonomies: A Bottom-Up Multi-Stage Approach via Semantic Clustering and Multi-Agent Collaboration](https://aclanthology.org/2025.emnlp-industry.113/) (Li et al., EMNLP 2025)

• Building Data-Driven Occupation Taxonomies: A Bottom-Up Multi-Stage Approach via Semantic Clustering and Multi-Agent Collaboration (Li et al., EMNLP 2025)

ACL

• Nan Li, Bo Kang, and Tijl De Bie. 2025. Building Data-Driven Occupation Taxonomies: A Bottom-Up Multi-Stage Approach via Semantic Clustering and Multi-Agent Collaboration. In Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing: Industry Track, pages 1596–1614, Suzhou (China). Association for Computational Linguistics.