Yejin Son

Hi! I’m Yejin Son, a Master student in Artificial Intelligence at the Yonsei University, MIRLAB advised by Youngjae Yu. I earned a B.S. in Economics and Applied Statistics from Yonsei University in 2023.

Research Interests

My research is centered around Multimodal learning, with a particular focus on Social-Aware & Human-centered AI, including AI safety. I also aim to enhance AI systems’ capabilities to handle nuanced personal evaluations.

Publications

EMNLP 2025 Main

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
Published in EMNLP 2025
[Paper]

EMNLP 2025 findings

Multimodal UNcommonsense: From Odd to Ordinary and Ordinary to Odd
Yejin Son*, Saejin Kim*, Dongjun Min, Youngjae Yu
Published in EMNLP 2025

COLM 2025

G1yphD3c0de: Towards Safer Language Models on Visually Perturbed Texts
Yejin Choi, Yejin Yeo, Yejin Son, Seungju Han, Youngjae Yu
Published in COLM 2025

Preprint

Mind the Motions: Benchmarking Theory‑of‑Mind in Everyday Body Language
Seungbeen Lee, Jinhong Jeong, Donghyun Kim, Yejin Son, Youngjae Yu
Coming Soon

EMNLP 2023

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
Published in EMNLP 2023
[Paper]