@inproceedings{abrougui-etal-2026-genefrdebate,
title = "{G}ene{FRD}ebate: Generated {F}rench Debates from News Articles with Industrial-Expert Summaries",
author = "Abrougui, Rim and
Lechien, Guillaume and
Savatier, Elisabeth and
Laurent, Beno{\^i}t",
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-1.143/",
doi = "10.63317/4zuibqqim37u",
pages = "1831--1841",
abstract = "Summarizing domain-specific conversations, such as political debates, remains challenging despite advances in large language models (LLMs), and resources for French debates are particularly limited. We present GeneFRDebate, a new dataset of synthetic French political debates generated from real-world news articles using an LLM, while keeping expert-written summaries unchanged. Our pipeline combines prompt engineering, human curation, and quality evaluation using both automatic metrics and expert assessment. We also provide baseline experiments with small-scale LLMs ({\ensuremath{\leq}}8B parameters), demonstrating the dataset{'}s usefulness for training and evaluation. This work shows that carefully generated synthetic data with human oversight can complement existing corpora, supporting research in multilingual and domain-specific dialogue summarization."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="abrougui-etal-2026-genefrdebate">
<titleInfo>
<title>GeneFRDebate: Generated French Debates from News Articles with Industrial-Expert Summaries</title>
</titleInfo>
<name type="personal">
<namePart type="given">Rim</namePart>
<namePart type="family">Abrougui</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Guillaume</namePart>
<namePart type="family">Lechien</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Elisabeth</namePart>
<namePart type="family">Savatier</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Benoît</namePart>
<namePart type="family">Laurent</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>Summarizing domain-specific conversations, such as political debates, remains challenging despite advances in large language models (LLMs), and resources for French debates are particularly limited. We present GeneFRDebate, a new dataset of synthetic French political debates generated from real-world news articles using an LLM, while keeping expert-written summaries unchanged. Our pipeline combines prompt engineering, human curation, and quality evaluation using both automatic metrics and expert assessment. We also provide baseline experiments with small-scale LLMs (\ensuremathłeq8B parameters), demonstrating the dataset’s usefulness for training and evaluation. This work shows that carefully generated synthetic data with human oversight can complement existing corpora, supporting research in multilingual and domain-specific dialogue summarization.</abstract>
<identifier type="citekey">abrougui-etal-2026-genefrdebate</identifier>
<identifier type="doi">10.63317/4zuibqqim37u</identifier>
<location>
<url>https://aclanthology.org/2026.lrec-1.143/</url>
</location>
<part>
<date>2026-05</date>
<extent unit="page">
<start>1831</start>
<end>1841</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T GeneFRDebate: Generated French Debates from News Articles with Industrial-Expert Summaries
%A Abrougui, Rim
%A Lechien, Guillaume
%A Savatier, Elisabeth
%A Laurent, Benoît
%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 abrougui-etal-2026-genefrdebate
%X Summarizing domain-specific conversations, such as political debates, remains challenging despite advances in large language models (LLMs), and resources for French debates are particularly limited. We present GeneFRDebate, a new dataset of synthetic French political debates generated from real-world news articles using an LLM, while keeping expert-written summaries unchanged. Our pipeline combines prompt engineering, human curation, and quality evaluation using both automatic metrics and expert assessment. We also provide baseline experiments with small-scale LLMs (\ensuremathłeq8B parameters), demonstrating the dataset’s usefulness for training and evaluation. This work shows that carefully generated synthetic data with human oversight can complement existing corpora, supporting research in multilingual and domain-specific dialogue summarization.
%R 10.63317/4zuibqqim37u
%U https://aclanthology.org/2026.lrec-1.143/
%U https://doi.org/10.63317/4zuibqqim37u
%P 1831-1841
Markdown (Informal)
[GeneFRDebate: Generated French Debates from News Articles with Industrial-Expert Summaries](https://aclanthology.org/2026.lrec-1.143/) (Abrougui et al., LREC 2026)
ACL