I study natural language processing. I am interested in dialogue
and generative models. The goals of my research
have spanned understanding cognition in the
human mind to making
information universally accessible to
people, all by advancing Artificial Intelligence.
Recently, I have been
working on factuality -- how can we get large language
models to speak the truth? I think that evaluation methods are
one important ingredient.
I work at Google DeepMind. Prior to that, I was
an Associate Professor at Penn State. I worked
at Carnegie Mellon University and hold a PhD
from the University of Edinburgh. If
you'd like to work with me (post-PhD) on NLP and
dialogue, please
apply to Google DeepMind.
