Hi! I'm Bagyasree.

I’m currently a Master’s student at CU Boulder, part of the BLAST lab led by Dr. Maria Pacheco. My overarching goal is to make language models safe and responsible by improving their social and moral intelligence. I’m particularly interested in helping them reason about implicit human behaviour, and aligning them with pluralistic human values. My work is interdisciplinary, drawing on ideas from linguistics and cognitive science to inform the methods I choose. I’m also interested in exploring how these ideas can be used to make models generalizable across domains. I’m looking for PhD positions!

I love books and stories; I think fiction is our richest source of information about the human condition, and one of the best ways to develop empathy for the world. Plus, they’re fun! Sometimes I post reviews about the books I’ve read on Goodreads. I’m also a bit of a crossword nerd, particularly the Cryptics.