Leveraging LLMs to Build a Semi-synthetic Dataset for Legal Information Retrieval: A Case Study on the Italian Civil Code and GPT-4oSep 1, 2025·Mattia Proietti,Lucia Passaro,Alessandro Lenci· 0 min read Cite URLTypeConference paperPublicationProceedings of the Eleventh Italian Conference on Computational Linguistics (Clic-it 2025)Last updated on Sep 1, 2025 On the proto-role properties inferred by transformer language models Jan 1, 2024 →