PriHA: A RAG-Enhanced LLM Framework for Primary Healthcare Assistant in Hong Kong
On the map: Retrieval-augmented generation → Medical and biomedical RAG
Abstract (arXiv)
To address the unsustainable rise in public health expenditures, the Hong Kong SAR Government is shifting its strategic focus to primary healthcare and encouraging citizens to use community resources to self-manage their health. However, official clinical guidelines are fragmented across disparate departments and formats, creating significant access barriers. While general-purpose Large Language Models (LLMs) such as ChatGPT and DeepSeek offer potential solutions for information accessibility, they are prone to generating factually inaccurate content due to a lack of localized and domain-specific knowledge. To this end, we propose a Retrieval-Augmented Generation-Enhanced LLM system as Primary Healthcare Assistant (PriHA) in Hong Kong. Specifically, a tri-stage pipeline is proposed that leverages a query optimizer to generalize user intent-oriented sub-queries, followed by a novel Dual Retrieval Augmented Generation (DRAG) architecture for mixed-source retrieval and context-reorganized generation. Comprehensive experiments and a detailed case study demonstrate that our proposed method can outperform both ablations and baseline in terms of accuracy and clarity. Our research provides a reliable and traceable dialogue retrieval framework for exploring other high-risk, localized application scenarios.
Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Medical and biomedical RAG, one of 15 directions in Retrieval-augmented generation. Builds on 14 of its 25 references that are in the map. First posted on arXiv 10 Apr 2026.
Builds on
14 of 25 references.
Closest ancestors · 2
Same direction, newest first
- 2026MedTutor: A Retrieval-Augmented LLM System for Case-Based Medical Education11 Jan
- 2024Benchmarking Retrieval-Augmented Generation for Medicine20 Feb
Other references · 12
- 2019Graph Neural Networks for Social Recommendationcited by 714
- 2024From Generation to Judgment: Opportunities and Challenges of LLM-as-a-judgecited by 494
- 2024A Survey on RAG Meeting LLMs: Towards Retrieval-Augmented Large Language Modelscited by 452
- 2023Recommender Systems in the Era of Large Language Models (LLMs)cited by 189
- 2024MediQ: Question-Asking LLMs and a Benchmark for Reliable Interactive Clinical Reasoningcited by 154
- 2025A Survey of WebAgents: Towards Next-Generation AI Agents for Web Automation with Large Foundation Modelscited by 87
- 2025Knowledge Graph Retrieval-Augmented Generation for LLM-based Recommendationcited by 57
- 2024TokenRec: Learning to Tokenize ID for LLM-based Generative Recommendationcited by 35
- 2025Diffusion Generative Recommendation with Continuous Tokenscited by 9
- 2025Retrieval-Augmented Purifier for Robust LLM-Empowered Recommendationcited by 7
- 2025Computational Protein Science in the Era of Large Language Models (LLMs)cited by 6
- 2025HD-Prot: A Protein Language Model for Joint Sequence-Structure Modeling with Continuous Structure Tokenscited by 4
Built on by
Not cited yet.
Similar, not cited
Close in wording, no citation either way
- 2025Conversation AI Dialog for Medicare powered by Finetuning and Retrieval Augmented Generation
- 2026A corpus-specific clinical RAG system matches or outperforms newer frontier LLMs on HealthBench
- 2026Healthier LLMs: Retrieval-Augmented Generation for Public Health Question Answering
- 2024The Geometry of Queries: Query-Based Innovations in Retrieval-Augmented Generation for Healthcare QA
- 2025Grounding Large Language Models in Clinical Evidence: A Retrieval-Augmented Generation System for Querying UK NICE Clinical Guidelines
- 2023MKRAG: Medical Knowledge Retrieval Augmented Generation for Medical Question Answering
- 2024Tool Calling: Enhancing Medication Consultation via Retrieval-Augmented Large Language Models
- 2024A MapReduce Approach to Effectively Utilize Long Context Information in Retrieval Augmented Language Models