We explore the Cultural Relevance of AI Models and Products by creating Datasets, Tools and Frameworks for Human-Centrered AI Evaluations
Building Culturally Relevant
& Responsible AI with...
Dataset and code
Dataset Curation
Nurtured by local qualitative and quantitative research
Building and open-sourcing locally relevant datasets through quantitative and qualitative research methods.
AI Model Fine-tuning
For specific sectors
Customizing models and AI agents for specific cultural contexts in Health, Education, and Financial inclusion.
Behavioral Research
On the usage of AI tools in Africa
Understanding how LLM and AI tools are perceived and utilized across African communities.
Research Projects
Research Papers
2026
Beyond Benchmarks: Scaling Multi-Turn Participatory AI Evaluations in Health and Education
Oluchi Audu, Oche Ankeli, Mame Coumba Ka, Ertony Basilwango, Millicent Ochieng, Mercy Muchai, Felermino Ali, Stephanie Nyairo
Workshop with Microsoft Research — Deep Learning Indaba 2026
Next-Billion AI Index: The Compass for AI Utility and Adoption in the Global Majority
Ambrish Rawat, Jessica He, Subhabrata Majumdar, Claudio Pinhanez, Yann Le Beux, Satyapriya Krishna, Rahul Gupta, Rumman Chowdhury, Kush R. Varshney
arXiv Preprint, 2026
AfriStereo: A Culturally Grounded Dataset for Evaluating Stereotypical Bias in Large Language Models
Yann Le Beux, Oluchi Audu, Oche Ankeli, Dhananjay Balakrishnan, Melissah Weya, Marie Daniella Ralaiarinosy
Proceedings of the Fifteenth Language Resources and Evaluation Conference — LREC 2026
Participatory and Culturally Grounded AI Evaluation for Health Use Cases within the African Context
Oluchi Audu, Melissah Weya, Sasha Ofori, Elizabeth Akpan, Yann Le Beux, Rajay Shah
AI Across Cultures Workshop — CHI 2026
Benchmarking Large Language Models on a Culturally Grounded Maternal Health QA Dataset from Senegal
Yann Le Beux, Camille Kramer-Courbariaux, Ertony Basilwango, Bineta Dieng
Poster Presentation — Deep Learning Indaba 2026
Ertony Basilwango, Oche Ankeli, Dhananjay Balakrishnan, Pierre Hervé Berdys, Yann Le Beux
Proceedings of the 7th Workshop on African Natural Language Processing — EACL 2026
2025
Alignment Debt: The Hidden Work of Making AI Usable
Cumi Oyemike, Elizabeth Akpan, Pierre Hervé-Berdys
Preprint, 2025
Camille Kramer-Courbariaux, Souadou Mane Sow, Yann Le Beux
Panel — International Conference on Family Planning, 2025
Ertony Basilwango, Oche Ankeli, Dhananjay Balakrishnan, Yann Le Beux
Poster — Deep Learning Indaba Conference 2025
Building African Stereotypes Datasets for Responsible AI Evaluation
Oluchi Audu, Melissah Weya, Marie Daniella Ralaiarinosy, Oche Ankeli, Dhananjay Balakrishnan, Yann Le Beux
Poster — Deep Learning Indaba Conference 2025
2024
The Transformative Potential of Participatory Research in International Development Programming
Oluchi Audu
EPIC Conference Proceedings, 2024
Yann Le Beux, Souadou Mane Sow
Workshop — ISS African Futures Conference 2024
2023
Navigating Adoption by Global South Users: The Case of Wikimedia Volunteers
Camille Kramer-Courbariaux, Sasha Ofori, Kalama Hafisou
EPIC Conference Proceedings, 2023
Links
Research Partners