Advait Deshmukh

Hi! I’m Advait, a Computer Science Ph.D. student at the University of Colorado Boulder, advised by Dr. Maria Antoniak. My research interests lie in Natural Language Processing, with a focus on Discourse Processing and Narrative Understanding. I’m broadly interested in the inductive biases we rely on to make sense of discourse — and how such insights can inform the design of better language technologies. I’m also drawn to narrative as a medium for storytelling and as a lens through which to study culture.

In my recent work at the CLS Lab, I studied how people iteratively rewrite their prompts to explore branching story possibilities with LLMs, drawing on naturally occurring conversations from WildChat — work appearing as The Garden of Forking Prompts at COLM 2026. I previously worked at — and continue to collaborate with — the BLAST Lab led by Dr. Maria Pacheco.

Outside of academia, I spent this past summer as an Applied Science Intern at Amazon in Bellevue, on the long-term planning and forecasting team within Supply Chain Optimization Technologies (SCOT), where I improved evaluation for their agentic systems. Previously, I worked for two years as a software engineer at Société Générale in Bangalore, where — among other things — I built a retrieval-augmented chat system that nudged me toward the NLP research I do today.

For fun, I like reading books, playing chess, and painting cat-sitting.