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
published a Space 6 days ago
saiteki-kai/prova updated a collection about 1 month ago
Streaming Safety Benchmarks updated a collection about 1 month ago
Streaming Safety BenchmarksOrganizations
BeaverTails Classifiers
Safety classifiers fine-tuned on a bilingual dataset composed of the English QA pairs from BeaverTails and the Italian QA pairs from BeaverTails-IT.
MT Models
Machine translation models
Italian Local Languages Datasets
Datasets automatically translated using Google Translate into Italian, Venetian, Lombard, Friulian, Ligurian, and Sicilian.
Italian LLMs
Large language models trained or fine-tuned on Italian language
MT Quality Estimation
Machine translation quality estimation (reference-free) metrics
Streaming Safety Benchmarks
Italian Local Languages Datasets
Datasets automatically translated using Google Translate into Italian, Venetian, Lombard, Friulian, Ligurian, and Sicilian.
BeaverTails Classifiers
Safety classifiers fine-tuned on a bilingual dataset composed of the English QA pairs from BeaverTails and the Italian QA pairs from BeaverTails-IT.
Italian LLMs
Large language models trained or fine-tuned on Italian language
MT Models
Machine translation models
MT Quality Estimation
Machine translation quality estimation (reference-free) metrics