Hey!
I'm a junior (third-year) at Princeton University studying computer science and math, and I'm grateful to be advised by Tom Griffiths in the Computational Cognitive Science Lab. I was born in the Bay Area 🌉 but have lived in Kingston, Ontario, Canada 🇨🇦 for my entire life.
Broadly speaking, I focus on how we can make AI, especially LLMs, more reliable, safe, and fair, to facilitate better human-AI interaction. Currently, I'm interested in how we can use cognitive science and psychology to reveal insightful patterns in human behavior — both the prosocial and the problematic — that offer lessons for building AI that adapts to us well without reproducing our worst tendencies.
I'm an incoming Research Intern at the Center for AI Safety this Summer (2026).
Outside of research, I like to play Wordle, Globle, Travle, GeoGuessr/Geotastic, and the NYT Mini. My life goal is to defeat the Ender Dragon in Minecraft Survival Mode.
Selected Publications
-
Are Large Language Models Sensitive to the Motives Behind Communication?
Addison J. Wu*, Ryan Liu*, Kerem Oktar*, Theodore R. Sumers, Thomas L. Griffiths
NeurIPS 2025 [Project Page] [arXiv]
Oral at PragLM @ COLM 2025 -
Mind Your Step (by Step): Chain-of-Thought can Reduce Performance on Tasks where Thinking Makes Humans Worse
Ryan Liu*, Jiayi Geng*, Addison J. Wu, Ilia Sucholutsky, Tania Lombrozo, Thomas L. Griffiths
ICML 2025 [Project Page] [arXiv]
Press coverage: The Information [text] -
Large Language Models Develop Novel Social Biases Through Adaptive Exploration
Addison J. Wu*, Ryan Liu*, Xuechunzi Bai, Thomas L. Griffiths
MTI-LLM @ NeurIPS 2025 [arXiv]
Where am I?
- San Francisco, CA 🇺🇸 - CAIS Internship (Jun-Aug 2026)
- San Diego, CA 🇺🇸 - NeurIPS (Dec 2025)
- Montreal, Canada 🇨🇦 - COLM (Oct 2025)
- Vancouver, Canada 🇨🇦 - ICML (Jul 2025)