@inproceedings{suozzi-etal-2026-remedy,
    title = "Can a Remedy Find a Researcher? Exploring the Development of Semantic Knowledge in {I}talian {B}aby{LM}s",
    author = "Suozzi, Alice  and
      Capone, Luca  and
      Lebani, Gianluca  and
      Lenci, Alessandro",
    editor = "Mohammad, Saif M.  and
      Ousidhoum, Nedjma",
    booktitle = "Proceedings of the 15th Joint Conference on Lexical and Computational Semantics (*{SEM} 2026)",
    month = jul,
    year = "2026",
    address = "San Diego, California, United States",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl-workshops/2026.starsem-conference.24/",
    pages = "366--377",
    ISBN = "979-8-89176-413-2",
    abstract = "A large body of research has examined the linguistic abilities of language models (LMs) across various languages. However, conclusive evidence regarding their semantic competence and world knowledge remains limited, especially for low-resource languages. In this study, we explore the semantic competence of Italian BabyLMs, focusing on their sensitivity to semantic violations. To this end, we adapt a minimal pair benchmark targeting semantic violations to evaluate the semantic abilities of BAMBI, a family of small-scale models trained on progressively larger and more complex datasets. We further compare their performance, assessed through accuracy, mean log-likelihood offset, and expected calibration error, with that of three larger Italian LMs. Our findings shed light on this aspect of semantic competence in small-scale models and how this is affected by data scale and training strategies."
}