paper7Atualizado em 21/11/2026 · English
← Todos os papers

Juru: Legal Brazilian Large Language Model from Reputable Sources

Roseval Malaquias Junior, Ramon Pires, Roseli Romero, Rodrigo Nogueira

Resumo

The high compute cost associated with pretraining large language models limits their research. Two strategies have emerged to address this issue: domain specialization and pretraining with high-quality data. To explore these strategies, we specialized the Mistral-7B model with 1.9 billion unique tokens from reputable Brazilian legal sources and conducted few-shot evaluations on legal and general knowledge test suites. Our model, Juru, demonstrates the benefits of domain specialization by achieving improved performance on legal benchmarks, even with a reduced amount of pretraining data. However…

De quem é

Outros papers das mesmas organizações