AMALIA 技术报告:面向欧洲葡萄牙语的全开源大语言模型
计算与语言
2026-03-30 v1 人工智能
机器学习
摘要
尽管开源大语言模型(LLM)取得了快速进展,但欧洲葡萄牙语(pt-PT)在训练数据和本土评估方面仍严重不足,机器翻译的基准测试可能忽略了该变体的语言和文化细微差别。我们介绍 AMALIA,一个全开源 LLM,优先考虑 pt-PT,通过在中期和后期训练阶段使用更多高质量的 pt-PT 数据。为更准确地评估 pt-PT,我们发布了一套 pt-PT 基准测试,包括翻译的标准任务和四个新数据集,分别针对 pt-PT 生成、语言能力和 pt-PT/pt-BR 偏见。实验表明,AMALIA 在翻译后的基准测试上与强大的基线相当,但在 pt-PT 特定评估方面显著提升,支持针对欧洲葡萄牙语进行针对性训练和本土化基准测试的决策。
引用
@article{arxiv.2603.26511,
title = {AMALIA Technical Report: A Fully Open Source Large Language Model for European Portuguese},
author = {Afonso Simplício and Gonçalo Vinagre and Miguel Moura Ramos and Diogo Tavares and Rafael Ferreira and Giuseppe Attanasio and Duarte M. Alves and Inês Calvo and Inês Vieira and Rui Guerra and James Furtado and Beatriz Canaverde and Iago Paulo and Vasco Ramos and Diogo Glória-Silva and Miguel Faria and Marcos Treviso and Daniel Gomes and Pedro Gomes and David Semedo and André Martins and João Magalhães},
journal= {arXiv preprint arXiv:2603.26511},
year = {2026}
}
备注
PROPOR 2026 - The 17th International Conference on Computational Processing of Portuguese