Excited to share that the Workshop on Trustworthy AI4GOOD will also be held at NeurIPS 2026 in Paris, where I’ll be serving on the program committee again!
Yejin Son
Incoming PhD Student
Computer Science, UBC NLP Group
Vector Institute
Introduction
Hi! I'm Yejin Son, an incoming PhD student in Computer Science at the University of British Columbia, where I will be advised by Vered Shwartz beginning in Fall 2026 and affiliated with the Vector Institute. I am currently completing my Master's in Artificial Intelligence at Yonsei University, advised by Prof. Youngjae Yu, where I also earned my B.A. in Economics and Applied Statistics. I was also a visiting researcher at the University of Toronto, working with Prof. Zhijing Jin.
News
I will be attending ICML 2026 Workshop with two workshop papers, presenting a poster on our work on latent cultural boundaries in LLMs at the Pluralistic Alignment Workshop, and our K-pop concert audience agent paper accepted as an oral at the Culture x AI Workshop. See you in Seoul!
I will be attending ACL 2026 to present our paper on counterfactual unfairness in LLMs through humor. See you in San Diego!
I am serving as a Program Chair of the ICML 2026 Workshop on Trustworthy AI4GOOD.
I am excited to share that I will be joining the UBC NLP Group as a PhD student in Computer Science, advised by Prof. Vered Shwartz, starting Fall 2026, supported by the Four Year Fellowship (4YF)!
Research
The Wedge Questions: Latent Cultural Boundaries in LLMs via Persona Projection Divergence
Yejin Son, Yongjin Yang, Ryan Faulkner, Matt Ratto, Seungwon Lim, Youngjae Yu, Zhijing Jin
Does Persona Make LLMs K-pop Fans? A Pilot Study of LLM-Based Online Concert Audience Agents
Kirak Kim, Hyojin Kim, Yejin Son, Sungyoung Kim, Kyung Myun Lee
Investigating Counterfactual Unfairness in LLMs towards Identities through Humor
Shubin Kim*, Yejin Son*, Junyeong Park, Keummin Ka, Seungbeen Lee, Jaeyoung Lee, Hyeju Jang, Alice Oh, Youngjae Yu
Mind the Motions: Benchmarking Theory-of-Mind in Everyday Body Language
Seungbeen Lee, Jinhong Jeong, Donghyun Kim, Yejin Son, Youngjae Yu
Subtle Risks, Critical Failures: A Framework for Diagnosing Physical Safety of LLMs for Embodied Decision Making
Yejin Son*, Minseo Kim*, Sungwoong Kim, Seungju Han, Jian Kim, Dongju Jang, Youngjae Yu, Chan Young Park
G1yphD3c0de: Towards Safer Language Models on Visually Perturbed Texts
Yejin Choi, Yejin Yeo, Yejin Son, Seungju Han, Youngjae Yu
Reading Books is Great, But Not if You Are Driving! Visually Grounded Reasoning about Defeasible Commonsense Norms
Seungju Han, Junhyeok Kim, Jack Hessel, Liwei Jiang, Jiwan Chung, Yejin Son, Yejin Choi, Youngjae Yu
About Me
Outside of research, I enjoy running and hiking. I also love cooking healthy meals.
Fun fact: I’ve coauthored two papers that each include at least two Yejins.