Year: 2026
Type: conference-paper
Abstract: We present Kenji-Endo, a BabyLM pretrained on a dedicated Italian dataset, which participated in four tasks at the 9th edition of EVALITA: DeSegMa, MultiPRIDE, IMPOLS, and FadeIT. Kenji-Endo achieved competitive performance across all tasks, demonstrating that language modeling with limited data and compact model sizes can represent a viable alternative to Large Language Models.
Institution: University of Turin
Language: English
Topic: Topic Modeling
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W7216643159