Hi! I am Sunny :)

I’m an undergraduate student majoring in Symbolic Systems and a coterminal student in Computer Science at Stanford University. I am very fortunate to be advised by Dan Jurafsky and Robert Hawkins.

I am deeply interested in questions at the intersection of human and machine cognition and how insights from computer science, cognitive science, linguistics, and philosophy can inform the development of safe and interpretable AI systems. My long-term research goal is to align AI models to augment – rather than constrain – the human intellect and autonomy.

Outside of research, here are some things that I love: good books (modernist, feminist, sci-fi, satirical), black tea, running, hiking (with four limbs when it’s really steep), racquet sports (but not pickeball), and playing Merlin or Oberon in Avalon. One of my biggest dreams is to write an autobiographical fiction.

Selected Papers

Generation Space Size: Understanding and Calibrating Open-Endedness of LLM Generations. Sunny Yu, Ahmad Jabbar, Robert Hawkins, Dan Jurafsky, Myra Cheng. Pre-print, under review (2025).

ELEPHANT: Measuring And Understanding Social Sycophancy in LLMs. Myra Cheng*, Sunny Yu*, Cinoo Lee, Pranav Khadpe, Lujain Ibrahim, Dan Jurafsky. Pre-print, under review (2025).

Generics Revisited: Analyzing Generalizations in Children’s Books and Caregivers’ Speech. Sunny Yu, Alvin Tan, Siying Zhang, Phllip Miao, Riley Carlson, Tobias Gerstenberg, David Rose. The 47th Annual Meeting of the Cognitive Science Society (2025).