Datasets automatically translated using Google Translate into Italian, Venetian, Lombard, Friulian, Ligurian, and Sicilian.
Giuseppe Magazzù
saiteki-kai
AI & ML interests
My research focuses on the developement of safety mitigation strategies and benchmarks for large language models.
Recent Activity
updated a collection 1 day ago
Italian Local Languages Datasets published a dataset 1 day ago
saiteki-kai/xstest-dialects published a dataset 1 day ago
saiteki-kai/mmlu-redux-dialectsOrganizations
Large language models trained or fine-tuned on Italian language
Machine translation quality estimation (reference-free) metrics
Datasets automatically translated using Google Translate into Italian, Venetian, Lombard, Friulian, Ligurian, and Sicilian.
Safety classifiers fine-tuned on a bilingual dataset composed of the English QA pairs from BeaverTails and the Italian QA pairs from BeaverTails-IT.
Large language models trained or fine-tuned on Italian language
Machine translation models
Machine translation quality estimation (reference-free) metrics