巴西语大模型新突破，法律与对话能力显著提升
Sabiá-4 Technical Report
- 四阶段训练：法律语料预训练+长上下文扩展至128K
- 在法律文书、多轮对话和工具使用上性能超越前代
- 适合需要低成本高精度巴西葡语应用的开发者
本技术报告介绍Sabiá-4和Sabiázinho-4两款新型葡萄牙语模型，专注巴西葡萄牙语。模型通过四阶段训练流程构建：在葡萄牙语及巴西法律语料上继续预训练，将上下文长度扩展至128K tokens，基于涵盖聊天、代码、法律任务和函数调用的指令数据进行监督微调，并完成偏好对齐。我们在六个基准类别上评估模型：巴西葡语对话能力、巴西立法知识、长上下文理解、指令遵循、标准化考试表现以及代理能力（含工具使用与网页导航）。结果表明，相较于其他模型，Sabiá-4和Sabiázinho-4在价格-性能权衡中表现优异，位于定价-准确率图表的左上区域。模型在法律文书撰写、多轮对话质量与代理任务完成度方面相较前代均有提升。
原文摘要 · Abstract (English)
This technical report presents Sabiá-4 and Sabiazinho-4, a new generation of Portuguese language models with a focus on Brazilian Portuguese language. The models were developed through a four-stage training pipeline: continued pre-training on Portuguese and Brazilian legal corpora, long-context extension to 128K tokens, supervised fine-tuning on instruction data spanning chat, code, legal tasks, and function calling, and preference alignment. We evaluate the models on six benchmark categories: conversational capabilities in Brazilian Portuguese, knowledge of Brazilian legislation, long-context understanding, instruction following, standardized exams, and agentic capabilities including tool use and web navigation. Results show that Sabiá-4 and Sabiazinho-4 achieve a favorable cost-performance trade-off compared to other models, positioning them in the upper-left region of the pricing-accuracy chart. The models show improvements over previous generations in legal document drafting, multi-turn dialogue quality, and agentic task completion.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。