04:00
2026-09-16
arxiv.org
large-language-models
Nepali Legal Expertise through Generative and Extractive Pre-trained Transformers (NepLEGiT)
Researchers introduced NepLEGiT, a 30-million-parameter Nepali legal small language model pre-trained from scratch on roughly 4 million tokens of Nepali legal text, reporting a cross-entropy loss of 0…