@inproceedings{simonetti-etal-2024-subcategorization,
    title = "Subcategorization of {I}talian Verbs with {LLM}s and {T}-{PAS}",
    author = "Simonetti, Luca  and
      Jezek, Elisabetta  and
      Vetere, Guido",
    editor = "Dell'Orletta, Felice  and
      Lenci, Alessandro  and
      Montemagni, Simonetta  and
      Sprugnoli, Rachele",
    booktitle = "Proceedings of the Tenth Italian Conference on Computational Linguistics (CLiC-it 2024)",
    month = dec,
    year = "2024",
    address = "Pisa, Italy",
    publisher = "CEUR Workshop Proceedings",
    url = "https://preview.aclanthology.org/ingest-emnlp/2024.clicit-1.99/",
    pages = "921--928",
    ISBN = "979-12-210-7060-6",
    abstract = "This study explores the application of Large Language Models (LLMs) to verb subcategorization in Italian, focusing on the identification and classification of syntactic patterns in sentences. While LLMs have made lexical analysis more implicit, explicit argument structure identification remains crucial in domain-specific contexts. The research leverages T-PAS, a rich lexical resource for Italian verbs, to fine-tune the open multilingual model Mistral 7B using the Iterative Reasoning Preference Optimization (IRPO) technique. This approach aims to enhance the recognition and extraction of verbal patterns from Italian sentences, addressing challenges in resource quality, coverage, and frame extraction methods. By combining curated lexical-semantic resources with neural language models, this work contributes to improving verb subcategorization tasks, particularly for the Italian language, and demonstrates the potential of LLMs in refining linguistic analysis tools."
}