On a mission to contribute to building AI that speaks every language’s truth, reflects cultural diversity, and ensures no voice gets lost in translation.

Hi! I’m Aditi, a first-year Computer Science Ph.D. student at McGill University and MILA – Quebec AI Institute, advised by Prof. Siva Reddy and Prof. Golnoosh Farnadi.

Before starting my Ph.D., I spent two years at Microsoft in the Turing Team, working with Prof. Monojit Choudhury on human-values alignment, ethical reasoning, value pluralism and foreign language effect in large language models (LLMs). I also contributed to building Bing Copilot Chat, focusing on conversation quality evaluations, developing and training next user message suggestions models, and worked on training of the state-of-the-art Visual Document Understanding model at Microsoft Turing. Before joining Microsoft, I completed my bachelor degree in Electrical Engineering from the Indian Institute of Technology Delhi.

My research interests lie in making language technologies more representative and adaptive to the complex interplay of languages and cultures. I aim to develop inclusive AI systems that equitably serve diverse global populations. I am also interested in plurastic human values alignment in LLMs. Additionally, I am passionate about expanding the general capabilities of language and multimodal models.