Addison J. Wu

Addison J. Wu

Undergrad @ Princeton

Email: addisonwu@princeton.edu (see this)

Hey!

I'm a junior (third-year) at Princeton University studying computer science and math, grateful to be advised by Tom Griffiths and Zhuang Liu. I was born in the Bay Area 🌉 and have lived in Kingston, Ontario, Canada 🇨🇦 for most of my life.

This summer, I will be joining the Center for AI Safety as a Research Intern.

My research studies the robustness and safety of foundation models to pave the way for human-compatible and socially beneficial AI systems. I also work on improving how we measure concrete progress across these fronts by creating more realistic evaluation paradigms.

Outside of research, I like to play Wordle, Globle, Travle, GeoGuessr/Geotastic, and the NYT Mini. I love binge-watching travel YouTubers who go off the beaten path (check out Harry Jaggard, Luke Damant, Britannica, Bald and Bankrupt). I'm working my way toward joining the Travelers Century Club (currently at 22)!

Publications

Peer-Reviewed

Large Language Models Develop Novel Social Biases Through Adaptive Exploration
Addison J. Wu*, Ryan Liu*, Xuechunzi Bai, Thomas L. Griffiths
ICML 2026 Spotlight; SPSP 2026 Invited Symposia Talk [arXiv]
Ads in AI Chatbots? An Analysis of How Large Language Models Navigate Conflicts of Interest
Addison J. Wu*, Ryan Liu*, Shuyue Stella Li, Yulia Tsvetkov, Thomas L. Griffiths
Agents in the Wild @ ICLR 2026 [arXiv]
Query Timing Produces Opposite Positional Biases Between LLMs and Humans
Jasin Cekinmez*, Addison J. Wu*, Thomas L. Griffiths
ICBINB @ ICLR 2026 Entropic Paper Award [Paper]
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; PragLM @ COLM 2025 Oral [Project Page] [arXiv]
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; Press coverage: The Information [Project Page] [arXiv] [text]
Toward a Neural Network-Based Approach for Improved Atmospheric Infrasound Source Localization
Addison J. Wu, Arnav Joshi, Jean-Pierre Hickey
IEEE Access, 2025 [Paper]

Preprints

In Plain Sight, Yet Missed: MLLMs Fail to Use Exact Visual Evidence
Jasin Cekinmez*, Addison J. Wu*, Ryo Mitsuhashi*, Linrong Cai*, Xingyu Fu, Zhuang Liu
under review, 2026
Quantifying Empirical Compute-Supervision Tradeoffs in RLVR
Ryo Mitsuhashi*, Patrick Chen*, Isabelle Tseng*, Jasin Cekinmez*, Addison J. Wu*
under review, 2026