University of New Brunswick · Faculty of Computer Science

Responsible AI.

A research lab at the University of New Brunswick advancing trustworthy, interpretable, and accountable AI — from explainability and safety to LLM-powered systems and agentic AI.

Explore Research → Join the Lab

Photo · UNB Fredericton Campus

— The Lab

The Responsible AI Research Lab (RAI) at the University of New Brunswick, led by Dr. Mahtab Sarvmaili, develops machine learning systems that are trustworthy, interpretable, and accountable. Our work spans the core pillars of responsible AI — explainability, privacy and safety, and security and robustness — and extends into LLM-powered systems and agentic AI, with applications in healthcare, law, and the public interest.

— 01 · Mission

Responsible AI is not merely an ethical aspiration — it is a technical necessity.

Responsible AI is not about building guidelines or ethics committees. It is about ensuring AI and machine learning systems actually work — correctly, reliably, and in the way we intend them to.

Achieving that requires a genuine, technical understanding of how AI systems learn, make decisions, and fail. That understanding is not an end in itself — it is the foundation that lets us adapt to real-world challenges across healthcare, law, and the public interest, and deploy systems that people can actually rely on.

— 02 · Foundations

Pillars of RAI research.

Our research is structured around three foundational pillars that together define what it means for an AI system to be responsibly deployed in the real world.