Belinda Li - "Eliciting Human Preferences with Language Models"

24 May 2024
Toronto Data Workshop
Belinda Li a PhD candidate at MIT CSAIL, affiliated with the language & intelligence (LINGO) lab @ MIT. Her work focuses on improving the human-interpretability, reliability, and usability of language models: examining and improving representations of both (objective) world states and (subjective) human preferences in language models. She is funded by an NDSEG Fellowship and Clare Boothe Luce Graduate Fellowship. Previously, she spent a year at Facebook AI Applied Research, and before that, obtained her B.S. in Computer Science at the University of Washington.