@article{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",
    journal = "International Conference on Language Resources and Evaluation",
    volume = "main",
    month = may,
    year = "2026",
    address = "Palma de Mallorca, Spain",
    publisher = "ELRA Language Resource Association",
    url = "https://preview.aclanthology.org/ingest-lrec/2026.lrec-main.143/",
    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."
}