@inproceedings{seifert-clematide-2026-scalable,
title = "A Scalable Pipeline for Novelty Detection in Skill Extraction Using Large Language Models",
author = "Seifert, Gian and
Clematide, Simon",
editor = "Piperidis, Stelios and
Bel, N{\'u}ria and
van den Heuvel, Henk and
Ide, Nancy and
Krek, Simon and
Toral, Antonio",
booktitle = "Proceedings of the Fifteenth Language Resources and Evaluation Conference",
month = may,
year = "2026",
address = "Palma de Mallorca, Spain",
publisher = "ELRA Language Resource Association",
url = "https://aclanthology.org/2026.lrec-1.611/",
doi = "10.63317/3twvjs5vmuwt",
pages = "7701--7706",
abstract = "The rapid evolution of the labor market requires skill ontologies to be continuously updated, but manually identifying emerging skills in job advertisements is highly labor-intensive. This paper presents a scalable, multi-stage pipeline for automated novelty detection in skill extraction. The system combines Large Language Models (LLMs) for candidate generation, a re-matching and threshold-based filtering module ({``}Turbo''), that compares candidates against the existing ontology, and a two-step aggregation process that merges string-based and embedding-based clustering. Experiments on Swiss job advertisement datasets using GPT-4o, Gemini-2.0-flash, and DeepSeek-V3 show that the pipeline effectively reduces noise and manual curation effort: Turbo filtering lowered false positives by 82{\%}, and aggregation reduced the number of items requiring review by 97{\%}. Among the tested models, Gemini-2.0-flash achieved the highest precision, reaching a novelty detection ratio of up to 73{\%} in the qualitative evaluation. These findings demonstrate the pipeline{'}s potential as an efficient tool for maintaining dynamic skill ontologies."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="seifert-clematide-2026-scalable">
<titleInfo>
<title>A Scalable Pipeline for Novelty Detection in Skill Extraction Using Large Language Models</title>
</titleInfo>
<name type="personal">
<namePart type="given">Gian</namePart>
<namePart type="family">Seifert</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>2026-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Fifteenth Language Resources and Evaluation Conference</title>
</titleInfo>
<name type="personal">
<namePart type="given">Stelios</namePart>
<namePart type="family">Piperidis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Núria</namePart>
<namePart type="family">Bel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Henk</namePart>
<namePart type="family">van den Heuvel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nancy</namePart>
<namePart type="family">Ide</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Simon</namePart>
<namePart type="family">Krek</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Antonio</namePart>
<namePart type="family">Toral</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>ELRA Language Resource Association</publisher>
<place>
<placeTerm type="text">Palma de Mallorca, Spain</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>The rapid evolution of the labor market requires skill ontologies to be continuously updated, but manually identifying emerging skills in job advertisements is highly labor-intensive. This paper presents a scalable, multi-stage pipeline for automated novelty detection in skill extraction. The system combines Large Language Models (LLMs) for candidate generation, a re-matching and threshold-based filtering module (“Turbo”), that compares candidates against the existing ontology, and a two-step aggregation process that merges string-based and embedding-based clustering. Experiments on Swiss job advertisement datasets using GPT-4o, Gemini-2.0-flash, and DeepSeek-V3 show that the pipeline effectively reduces noise and manual curation effort: Turbo filtering lowered false positives by 82%, and aggregation reduced the number of items requiring review by 97%. Among the tested models, Gemini-2.0-flash achieved the highest precision, reaching a novelty detection ratio of up to 73% in the qualitative evaluation. These findings demonstrate the pipeline’s potential as an efficient tool for maintaining dynamic skill ontologies.</abstract>
<identifier type="citekey">seifert-clematide-2026-scalable</identifier>
<identifier type="doi">10.63317/3twvjs5vmuwt</identifier>
<location>
<url>https://aclanthology.org/2026.lrec-1.611/</url>
</location>
<part>
<date>2026-05</date>
<extent unit="page">
<start>7701</start>
<end>7706</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T A Scalable Pipeline for Novelty Detection in Skill Extraction Using Large Language Models
%A Seifert, Gian
%A Clematide, Simon
%Y Piperidis, Stelios
%Y Bel, Núria
%Y van den Heuvel, Henk
%Y Ide, Nancy
%Y Krek, Simon
%Y Toral, Antonio
%S Proceedings of the Fifteenth Language Resources and Evaluation Conference
%D 2026
%8 May
%I ELRA Language Resource Association
%C Palma de Mallorca, Spain
%F seifert-clematide-2026-scalable
%X The rapid evolution of the labor market requires skill ontologies to be continuously updated, but manually identifying emerging skills in job advertisements is highly labor-intensive. This paper presents a scalable, multi-stage pipeline for automated novelty detection in skill extraction. The system combines Large Language Models (LLMs) for candidate generation, a re-matching and threshold-based filtering module (“Turbo”), that compares candidates against the existing ontology, and a two-step aggregation process that merges string-based and embedding-based clustering. Experiments on Swiss job advertisement datasets using GPT-4o, Gemini-2.0-flash, and DeepSeek-V3 show that the pipeline effectively reduces noise and manual curation effort: Turbo filtering lowered false positives by 82%, and aggregation reduced the number of items requiring review by 97%. Among the tested models, Gemini-2.0-flash achieved the highest precision, reaching a novelty detection ratio of up to 73% in the qualitative evaluation. These findings demonstrate the pipeline’s potential as an efficient tool for maintaining dynamic skill ontologies.
%R 10.63317/3twvjs5vmuwt
%U https://aclanthology.org/2026.lrec-1.611/
%U https://doi.org/10.63317/3twvjs5vmuwt
%P 7701-7706
Markdown (Informal)
[A Scalable Pipeline for Novelty Detection in Skill Extraction Using Large Language Models](https://aclanthology.org/2026.lrec-1.611/) (Seifert & Clematide, LREC 2026)
ACL