mlsanityData to 14 Oct 2026

HKGAI-V1: Towards Regional Sovereign Large Language Model for Hong Kong

arXiv 2507.11502 ↗First posted 14 Jul 2025cs.CL cs.CE cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 45 of its 63 references that are in the map. First posted on arXiv 14 Jul 2025.

Builds on

45 of 63 references.

References · 45

  1. 2023GPT-4 Technical Reportcited by 18,396
  2. 2022Training language models to follow instructions with human feedbackcited by 15,971
  3. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,297
  4. 2023Direct Preference Optimization: Your Language Model is Secretly a Reward Modelcited by 8,065
  5. 2020Measuring Massive Multitask Language Understandingcited by 7,963
  6. 2025DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learningcited by 6,330
  7. 2024Gemini 1.5: Unlocking multimodal understanding across millions of tokens of contextcited by 3,224
  8. 2023Retrieval-Augmented Generation for Large Language Models: A Surveycited by 2,212
  9. 2024MMLU-Pro: A More Robust and Challenging Multi-Task Language Understanding Benchmarkcited by 1,848
  10. 2024From Local to Global: A Graph RAG Approach to Query-Focused Summarizationcited by 1,453
  11. 2021A General Language Assistant as a Laboratory for Alignmentcited by 1,055
  12. 2023BeaverTails: Towards Improved Safety Alignment of LLM via a Human-Preference Datasetcited by 860
33 more
  1. 2023Diffusion Model Alignment Using Direct Preference Optimizationcited by 790
  2. 2023AGIEval: A Human-Centric Benchmark for Evaluating Foundation Modelscited by 716
  3. 2020Artificial Intelligence, Values and Alignmentcited by 448
  4. 2024Understanding the planning of LLM agents: A surveycited by 421
  5. 2023RLHF-V: Towards Trustworthy MLLMs via Behavior Alignment from Fine-grained Correctional Human Feedbackcited by 412
  6. 2023AI Alignment: A Comprehensive Surveycited by 263
  7. 2024PKU-SafeRLHF: Towards Multi-Level Safety Alignment for LLMs with Human Preferencecited by 261
  8. 2025Agentic Retrieval-Augmented Generation: A Survey on Agentic RAGcited by 249
  9. 2024Chain of Agents: Large Language Models Collaborating on Long-Context Taskscited by 206
  10. 2022Fine-tuning language models to find agreement among humans with diverse preferencescited by 189
  11. 2020Open Problems in Cooperative AIcited by 168
  12. 2024FlashRAG: A Modular Toolkit for Efficient Retrieval-Augmented Generation Researchcited by 166
  13. 2018Supervising strong learners by amplifying weak expertscited by 145
  14. 2023Cultural Alignment in Large Language Models: An Explanatory Analysis Based on Hofstede's Cultural Dimensionscited by 112
  15. 2024Aligner: Efficient Alignment by Learning to Correctcited by 98
  16. 2025AgentNet: Decentralized Evolutionary Coordination for LLM-based Multi-Agent Systemscited by 90
  17. 2024A Review of Prominent Paradigms for LLM-Based Agents: Tool Use (Including RAG), Planning, and Feedback Learningcited by 74
  18. 2024Align Anything: Training All-Modality Models to Follow Instructions with Language Feedbackcited by 39
  19. 2023Flames: Benchmarking Value Alignment of LLMs in Chinesecited by 37
  20. 2025PrivaCI-Bench: Evaluating Privacy with Contextual Integrity and Legal Compliancecited by 37
  21. 2024SafeSora: Towards Safety Alignment of Text2Video Generation via a Human Preference Datasetcited by 35
  22. 2025Retrieval Augmented Generation and Understanding in Vision: A Survey and New Outlookcited by 32
  23. 2020Value Alignment Verificationcited by 20
  24. 2018Building Ethics into Artificial Intelligencecited by 19
  25. 2024Multilingual Large Language Models: A Systematic Surveycited by 18
  26. 2024Sequence to Sequence Reward Modeling: Improving RLHF by Language Feedbackcited by 9
  27. 2024On the Modeling Capabilities of Large Language Models for Sequential Decision Makingcited by 9
  28. 2025SafeLawBench: Towards Safe Alignment of Large Language Modelscited by 9
  29. 2025FRAG: A Flexible Modular Framework for Retrieval-Augmented Generation based on Knowledge Graphscited by 8
  30. 2025Context Reasoner: Incentivizing Reasoning Capability for Contextualized Privacy and Safety Compliance via Reinforcement Learningcited by 8
  31. 2025Benchmarking Multi-National Value Alignment for Large Language Modelscited by 7
  32. 2024Building Decision Making Models Through Language Model Regimecited by 2
  33. 2025Measuring Hong Kong Massive Multi-Task Language Understandingcited by 1

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025Aligning LLMs for Multilingual Consistency in Enterprise Applications
  2. 2026PriHA: A RAG-Enhanced LLM Framework for Primary Healthcare Assistant in Hong Kong
  3. 2024Responsible Multilingual Large Language Models: A Survey of Development, Applications, and Societal Impact
  4. 2026Typhoon-S: Minimal Open Post-Training for Sovereign Large Language Models
  5. 2026Analyzing performance of Retrieval Augmented Generation models for Question Answering Tasks
  6. 2024Leveraging Retrieval-Augmented Generation for Culturally Inclusive Hakka Chatbots: Design Insights and User Perceptions
  7. 2024Deploying Large Language Models With Retrieval Augmented Generation
  8. 2024A Survey on RAG Meeting LLMs: Towards Retrieval-Augmented Large Language Models