Research library

The research behind Brilla AI.

Papers exploring the challenge of building an AI contestant for Ghana’s National Science and Maths Quiz, from the original challenge to the Brilla AI system.

International Conference on Artificial Intelligence in Education2026

NSMQ Riddles: A Benchmark of Scientific and Mathematical Riddles for Quizzing Large Language Models

George Boateng, Naafi Dasana Ibrahim, Samuel John, Philemon Badu, Patrick Agyeman-Budu, Jonathan Abrefah Mensah, Kevin Takyi Yeboah, William Edor, Andrew Kojo Mensah-Onumah, Nana Sam Yeboah, and Victor Kumbol

Introduces a Ghanaian benchmark of scientific and mathematical riddles from the National Science and Maths Quiz for evaluating large language models in an underrepresented educational context.

Read arXiv paper

PML4DC at ICLR 20232023

Can an AI Win Ghana’s National Science and Maths Quiz? An AI Grand Challenge for Education

George Boateng, Victor Kumbol, and Elsie Effah Kaufmann

Introduces the AI Grand Challenge for Education and frames Ghana’s National Science and Maths Quiz as a demanding real-world test for multimodal AI.

Read workshop paper

Deep Learning Indaba 20232023

Towards an AI to Win Ghana’s National Science and Maths Quiz

George Boateng, Jonathan Abrefah Mensah, Kevin Takyi Yeboah, William Edor, Andrew Kojo Mensah-Onumah, Naafi Dasana Ibrahim, and Nana Sam Yeboah

Presents the research direction and engineering challenges behind building an AI contestant for live NSMQ competition.

Read OpenReview paper

AIED 20242024

Brilla AI: AI Contestant for the National Science and Maths Quiz

George Boateng, Jonathan Abrefah Mensah, Kevin Takyi Yeboah, William Edor, Andrew Kojo Mensah-Onumah, Naafi Dasana Ibrahim, and Nana Sam Yeboah

Describes Brilla AI’s open system for listening, understanding, reasoning, and responding to NSMQ questions in real time.

Read arXiv paper