Tokenless

Low resource languages

Session on Inclusive AI: Data, Models, Evaluation

Session on Inclusive AI: Data, Models, Evaluation

The Microsoft Research India Academic Research Summit 2026 session on "Inclusive AI" explored critical challenges in developing AI that serves diverse linguistic and cultural contexts. Speakers Niloy Ganguly, Danish Pruthi, Sunayana Sitaram, Anoop Kunchukuttan, and Ashutosh Modi addressed data gaps, model biases, and evaluation shortcomings, emphasizing the need for equitable and culturally relevant AI. Key themes included the use of synthetic data for low-resource languages, the impact of tokenization on model performance, geographical disparities in generative AI, and the application of AI for social good in legal and accessibility domains. The discussions underscored the importance of community involvement, open data, and designing AI for multilinguality from the outset, rather than as an afterthought.

Beyond Swahili: Designing Inclusive AI for Bantu Languages

Beyond Swahili: Designing Inclusive AI for Bantu Languages

Alfred Malingo discusses the unique position of Swahili in AI, arguing that its structural similarities to other Bantu languages make it a far more effective pivot language than English for developing inclusive and accurate models. He deconstructs the failures of typologically mismatched transfer from Indo-European languages and presents a case study, AfriMT-a, to demonstrate how Swahili can serve as a technical bridge for machine translation and representation learning across the Bantu language family.

Building Better Language Models Through Global Understanding

Building Better Language Models Through Global Understanding

Dr. Mazi Fadai discusses the critical challenges in multilingual AI, including data imbalances and flawed evaluation methodologies. She argues that tackling these difficult multilingual problems is not only essential for global accessibility but also a catalyst for fundamental AI innovation, much like how machine translation research led to the Transformer architecture. The talk introduces new, more culturally aware evaluation benchmarks like Global MMLU and INCLUDE as a path toward building more robust and globally representative language models.