为香港定制的主权大模型,兼顾本地语言与法律文化。
HKGAI-V1: Towards Regional Sovereign Large Language Model for Hong Kong
- 基于DeepSeek架构,全参数微调适配香港多语环境。
- 在本地敏感问题上表现优于通用模型,具备治理嵌入特性。
- 提供可复用的区域AI开发框架,适合政府与教育机构参考。
本文介绍了HKGAI-V1的构建,这是为香港量身打造的基础性主权大语言模型,旨在建立符合本地价值观的AI基础设施。针对香港独特的双语(粤语、普通话)与多语(英文)环境、'一国两制'下的社会法律背景及本地文化价值需求,模型基于DeepSeek架构,通过多维度全参数微调实现区域规范对齐,并集成检索增强生成(RAG)系统以确保信息时效性与准确性。核心贡献在于设计并实现了一套完整的区域性AI对齐与安全框架,体现在两大成果:1)成功开发出HKGAI-V1,其在处理香港特有文化敏感问题上超越通用模型,体现‘治理嵌入’式数字主权,赋能公共事务、法律与教育等关键领域自主可控;2)创建专有的对抗性香港价值基准测试集(Adversarial HK Value Benchmark),用于在挑战性条件下评估模型对本地伦理与法律标准的遵循程度。本文不仅提供技术成果,更输出一套可复制的区域性人工智能系统开发蓝图。
原文摘要 · Abstract (English)
This paper presents the development of HKGAI-V1, a foundational sovereign large language model (LLM), developed as part of an initiative to establish value-aligned AI infrastructure specifically tailored for Hong Kong. Addressing the region's unique multilingual environment (Cantonese, Mandarin, and English), its distinct socio-legal context under the "one country, two systems" framework, and specific local cultural and value considerations, the model is built upon the DeepSeek architecture and systematically aligned with regional norms through a multifaceted full parameter fine-tuning process. It is further integrated with a retrieval-augmented generation (RAG) system to ensure timely and factually grounded information access. The core contribution lies in the design and implementation of a comprehensive, region-specific AI alignment and safety framework, demonstrated through two key achievements: 1) The successful development of HKGAI-V1 itself - which outper-forms general-purpose models in handling Hong Kong-specific culturally sensitive queries, and embodies a "governance-embedded" approach to digital sovereignty - empowers Hong Kong to exercise control over AI applications in critical sectors including public services, legal systems, and edu-cation. 2) The development of the proprietary Adversarial HK Value Benchmark, a rigorous tool for evaluating model alignment with local ethical and legal stand-ards under challenging conditions. By documenting these achievements, the paper provides not only a technological artifact but also a replicable blueprint for developing advanced, regionally focused AI systems deeply rooted in their local identities.
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。