@inproceedings{gnehm-clematide-2025-improving,
title = "Improving Occupational {ISCO} Classification of Multilingual {S}wiss Job Postings with {LLM}-Refined Training Data",
author = "Gnehm, Ann-Sophie and
Clematide, Simon",
editor = "Che, Wanxiang and
Nabende, Joyce and
Shutova, Ekaterina and
Pilehvar, Mohammad Taher",
booktitle = "Findings of the Association for Computational Linguistics: ACL 2025",
month = jul,
year = "2025",
address = "Vienna, Austria",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.findings-acl.1124/",
doi = "10.18653/v1/2025.findings-acl.1124",
pages = "21834--21847",
ISBN = "979-8-89176-256-5",
abstract = "Classifying occupations in multilingual job postings is challenging due to noisy labels, language variation, and domain-specific terminology. We present a method that refines silver-standard ISCO labels by consolidating them with predictions from pre-fine-tuned models, using large language model (LLM) evaluations to resolve discrepancies. The refined labels are used in Multiple Negatives Ranking (MNR) training for SentenceBERT-based classification. This approach substantially improves performance, raising Top-1 accuracy on silver data from 37.2{\%} to 58.3{\%} and reaching up to 80{\%} precision on held-out data{---}an over 30-point gain validated by both GPT and human raters. The model benefits from cross-lingual transfer, with particularly strong gains in French and Italian. These results demonstrate hat LLM-guided label refinement can substantially improve multilingual occupation classification in fine-grained taxonomies such as CH-ISCO with 670 classes."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="gnehm-clematide-2025-improving">
<titleInfo>
<title>Improving Occupational ISCO Classification of Multilingual Swiss Job Postings with LLM-Refined Training Data</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ann-Sophie</namePart>
<namePart type="family">Gnehm</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Simon</namePart>
<namePart type="family">Clematide</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>Classifying occupations in multilingual job postings is challenging due to noisy labels, language variation, and domain-specific terminology. We present a method that refines silver-standard ISCO labels by consolidating them with predictions from pre-fine-tuned models, using large language model (LLM) evaluations to resolve discrepancies. The refined labels are used in Multiple Negatives Ranking (MNR) training for SentenceBERT-based classification. This approach substantially improves performance, raising Top-1 accuracy on silver data from 37.2% to 58.3% and reaching up to 80% precision on held-out data—an over 30-point gain validated by both GPT and human raters. The model benefits from cross-lingual transfer, with particularly strong gains in French and Italian. These results demonstrate hat LLM-guided label refinement can substantially improve multilingual occupation classification in fine-grained taxonomies such as CH-ISCO with 670 classes.</abstract>
<identifier type="citekey">gnehm-clematide-2025-improving</identifier>
<identifier type="doi">10.18653/v1/2025.findings-acl.1124</identifier>
<location>
<url>https://aclanthology.org/2025.findings-acl.1124/</url>
</location>
<part>
<date>2025-07</date>
<extent unit="page">
<start>21834</start>
<end>21847</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Improving Occupational ISCO Classification of Multilingual Swiss Job Postings with LLM-Refined Training Data
%A Gnehm, Ann-Sophie
%A Clematide, Simon
%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 gnehm-clematide-2025-improving
%X Classifying occupations in multilingual job postings is challenging due to noisy labels, language variation, and domain-specific terminology. We present a method that refines silver-standard ISCO labels by consolidating them with predictions from pre-fine-tuned models, using large language model (LLM) evaluations to resolve discrepancies. The refined labels are used in Multiple Negatives Ranking (MNR) training for SentenceBERT-based classification. This approach substantially improves performance, raising Top-1 accuracy on silver data from 37.2% to 58.3% and reaching up to 80% precision on held-out data—an over 30-point gain validated by both GPT and human raters. The model benefits from cross-lingual transfer, with particularly strong gains in French and Italian. These results demonstrate hat LLM-guided label refinement can substantially improve multilingual occupation classification in fine-grained taxonomies such as CH-ISCO with 670 classes.
%R 10.18653/v1/2025.findings-acl.1124
%U https://aclanthology.org/2025.findings-acl.1124/
%U https://doi.org/10.18653/v1/2025.findings-acl.1124
%P 21834-21847
Markdown (Informal)
[Improving Occupational ISCO Classification of Multilingual Swiss Job Postings with LLM-Refined Training Data](https://aclanthology.org/2025.findings-acl.1124/) (Gnehm & Clematide, Findings 2025)
ACL