Research
Published work
and active inquiry.
Mo is an active AI/ML researcher whose work focuses on responsible AI, fairness in language models, and the equitable development of AI systems for underserved communities.
Research Focus
What Mo studies.
Responsible AI
The ethical development and deployment of AI systems, with emphasis on accountability, transparency, and harm prevention.
LLM Fairness
Bias measurement and mitigation in large language models. Ensuring AI systems produce equitable outputs across demographic groups.
AI for Global Health
How AI systems can serve marginalised and underserved communities, particularly in African and low-resource contexts.
Publications & Projects
Selected research output.
Paper · In Progress
DeployStega: Covert LLM Communication via GitHub
A novel system for covert communication between large language models using GitHub's collaborative environment as a steganographic channel. Targeting ACL conference format. Co-authored with research collaborators including Srikanth, Menon, and Howes.
Research Programme · Completed
LLM Fairness — Algoverse AI Research Program
Research into bias, fairness, and equity in large language models. Completed as part of the Algoverse AI Research Program. Focuses on measuring and mitigating demographic bias in model outputs.
Journal Publication · 2020
International Journal of Computer
Published research contributing to the field. Part of Mo's foundational academic output, establishing her early presence in the research community before her graduate studies.
MSc Research · University of Birmingham
Responsible AI & LLM Ethics — Google DeepMind Scholar
Graduate research conducted as a Google DeepMind Scholar at the University of Birmingham. Focus on responsible AI development, ethical implications of machine learning systems, and LLM fairness in real-world deployment.
Collaborate
Interested in research collaboration?
Mo is open to research partnerships in responsible AI, LLM fairness, and AI for global health.