@inproceedings{tamburini-2025-curated,
title = "Curated Data Does Not Mean Representative Data When Training Large Language Models: An Experiment Using Representative Data for {I}talian",
author = "Tamburini, Fabio",
editor = "Bosco, Cristina and
Jezek, Elisabetta and
Polignano, Marco and
Sanguinetti, Manuela",
booktitle = "Proceedings of the Eleventh Italian Conference on Computational Linguistics (CLiC-it 2025)",
month = sep,
year = "2025",
address = "Cagliari, Italy",
publisher = "CEUR Workshop Proceedings",
url = "https://preview.aclanthology.org/sigarab-more-entries-6621/2025.clicit-1.104/",
pages = "1102--1111",
ISBN = "979-12-243-0587-3"
}Markdown (Informal)
[Curated Data Does Not Mean Representative Data When Training Large Language Models: An Experiment Using Representative Data for Italian](https://preview.aclanthology.org/sigarab-more-entries-6621/2025.clicit-1.104/) (Tamburini, CLiC-it 2025)
ACL