I'm a Ph.D. student at Sungkyunkwan University, advised by Prof. JinYeong Bak. I am broadly interested in building AI systems that can reason and act robustly and efficiently in real-world scenarios. I also explore how to equip these systems with human values and emotions.
Distributional Open-Ended Evaluation of LLM Cultural Value Alignment Based on Value Codebook
Jaehyeok Lee, Xiaoyuan Yi, Jing Yao, Hyunjin Hwang, Roy Ka-Wei Lee, Xing Xie, JinYeong Bak
ICML 2026 (To appear) [Paper]
Enhancing Emotion-Cause Pair Extraction in Conversation with Contextual Information
Jaehyeok Lee, JinYeong Bak
SAC 2026 (To appear)
Unintended Harms of Value-Aligned LLMs: Psychological and Empirical Insights
Sooyung Choi*, Jaehyeok Lee*, Xiaoyuan Yi, Jing Yao, Xing Xie, JinYeong Bak (*: equal contribution)
ACL 2025 (🎤 oral & panel; 0.8% of accepted papers) [Paper]
Camellia: Benchmarking Cultural Biases in LLMs for Asian Languages
Tarek Naous, Anagha Savit, Carlos Rafael Catalan, Geyang Guo, Jaehyeok Lee, Kyungdon Lee, Lheane Marie Dizon, Mengyu Ye, Neel Kothari, Sahajpreet Singh, Sarah Masud, Tanish Patwa, Trung Thanh Tran, Zohaib Khan, Alan Ritter, JinYeong Bak, Keisuke Sakaguchi, Tanmoy Chakraborty, Yuki Arase, Wei Xu
arXiv 2025 [Paper]
Sungkyunkwan University (Mar 2025 – Present)
Ph.D. Student, Artificial Intelligence
Advised by Prof. JinYeong Bak
Sungkyunkwan University (Mar 2023 – Feb 2025)
M.S., Artificial Intelligence
Advised by Prof. JinYeong Bak
Sungkyunkwan University (Mar 2017 – Feb 2023)
B.S., Computer Science and Engineering
B.S., Chemical Engineering
Unintended Harms of Value-Aligned LLMs (Nov 2025)
SKKU Seminar in Computer Engineering
Psychological and Empirical Insights on the Harms of Aligning LLMs with Human Values (Jul 2025)
Microsoft Research Asia Intern Tech Talk
Device and method for generating emotion-cause pair based on conversation, and storage medium storing instruction to perform method for generating emotion cause pair
DongJin Jeong, JinYeong Bak, Jaehyeok Lee
United States Patent Application [Link]