@inproceedings{pascucci-tavosanis-2024-confronto,
    title = "Confronto tra Diversi Tipi di Valutazione del Miglioramento della Chiarezza di Testi Amministrativi in Lingua Italiana",
    author = "Pascucci, Mariachiara  and
      Tavosanis, Mirko",
    editor = "Dell'Orletta, Felice  and
      Lenci, Alessandro  and
      Montemagni, Simonetta  and
      Sprugnoli, Rachele",
    booktitle = "Proceedings of the 10th Italian Conference on Computational Linguistics (CLiC-it 2024)",
    month = dec,
    year = "2024",
    address = "Pisa, Italy",
    publisher = "CEUR Workshop Proceedings",
    url = "https://preview.aclanthology.org/jlcl-multiple-ingestion/2024.clicit-1.81/",
    pages = "746--756",
    language = "ita",
    ISBN = "979-12-210-7060-6",
    abstract = "The paper presents a comparison of different types of evaluation of administrative texts in the Italian language on which a clarity improvement intervention was carried out. The clarity improvement was performed by human experts and ChatGPT. The evaluation was carried out in four different ways: by expert evaluators, used as a reference; by evaluators with good skills, subject to dedicated training; by generic evaluators recruited through a crowdsourcing platform; by ChatGPT. The results show that the closest match to the results of the evaluation by expert evaluators was reached, by a wide margin, by evaluators with good skills and dedicated training; the second best approach was reached by requesting evaluation from ChatGPT; the worst approach was reached by generic evaluators recruited through a crowdsourcing platform. Task features that may have influenced the outcome are also discussed."
}