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

PoETa v2: Toward More Robust Evaluation of Large Language Models in Portuguese

Thales Sales Almeida, Ramon Pires, Hugo Abonizio, Rodrigo Nogueira, Hélio Pedrini

Resumo

Large Language Models (LLMs) exhibit significant variations in performance across linguistic and cultural contexts, underscoring the need for systematic evaluation in diverse languages. In this work, we present the most extensive evaluation of LLMs for the Portuguese language to date. Leveraging our newly introduced PoETa v2 benchmark -- a comprehensive suite of over 40 tasks in Portuguese -- we assess more than 20 models covering a broad spectrum of training scales and computational resources. Our study reveals how computational investment and language-specific adaptation impact performance i…

De quem é

Outros papers das mesmas organizações