Operationalizing LLMs & RAG for Public Health: Building Reliable, Deployable Systems

Mission and objectives

---

The objective of this workshop is to explore the practical deployment, infrastructure needs, and operational challenges of using Large Language Models (LLMs) and Retrieval-Augmented Generation (RAG) systems in digital public health. In public-health contexts, the cost of hallucinations, strict data governance requirements, and the need for trustworthy, auditable outputs introduce constraints that are fundamentally different from general-purpose LLM applications. While the main conference track focuses on methodological and ethical advances in AI for health, this workshop specifically targets the engineering, implementation, and real-world integration of RAG-based systems that can support reliable decision-making, surveillance workflows, and field operations under these constraints, with emphasis on robust retrieval pipelines, evaluation frameworks, and deployment in real operational settings.

Target Audience

---

Submissions and participation are welcome including:

• Data scientists and ML/LLM practitioners
• Engineers building LLM/RAG systems
• Researchers in AI safety and health governance
• Industry partners in AI for healthcare

Format (proposed)

---

The workshop will include:

• A panel discussion chaired by Dr. Aisha Abdullah Aldosery
• Paper oral presentations selected through a competitive review process
• A Best Paper Award
• Fully in-person delivery

Speakers

---

---