Advait Deshmukh

Hi! I’m Advait, a Computer Science Ph.D. student at the University of Colorado Boulder, advised by Dr. Maria Antoniak in the CLS Lab. I work on language technology: the inductive biases these systems rely on, and the assumptions people make about what they’re capable of. So far, I’ve studied what limitations language models inherit from their training distributions (All Entities are Not Created Equal), and how people engage with them for story generation, using conversations from WildChat (The Garden of Forking Prompts).

I am particularly interested in working with narrative and discourse. Partly because I love fiction. Partly it’s that discourse is hard: coherence and diversity can be tricky to define, and in an era of RLVR, this subjectivity makes it a compelling problem.

Previously, I worked with Dr. Maria Pacheco at the BLAST Lab, interned at Amazon, and spent two years as a software engineer at Société Générale.

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