Yoon Kyung Lee

Empathic AI, Affective Science, Cognitive Science,
Social Robots, Natural Language Processing, Artificial Intelligence


Professional Experiences:
  • Research Professional, University of Texas at Austin, Austin, USA. Sept 2023 - Aug 2024
  • Lecturer, Samsung Design and Art Institute (SADI), Seoul, Korea. June 2022 - Sept 2022
  • Reviewer, PRESENCE: Virtual and Augmented Reality, Korean Journal of Cognitive Science, Cognitive Science Society (CogSci)
  • Python Instructor, Self-Paced Learning & Tutoring Program, Department of Engineering, Seoul National University, Seoul, Korea. Spring 2019
  • Instructor, Faculty IT Education Program, Ajou University, Suwon, Korea. March 2019
  • Teaching Assistant, <Psychology and AI>, Korean Massive Open Online Course (K-MOOC) by Ministry of Education, Korea. 2019 - 2023

Education:
  • Ph.D. Cand. in Cognitive Psychology (Minor: Quantitative Psychology), Seoul National University
  • M.A. in Cognitive Psychology, Seoul National University
  • B.S. in Psychology, The University of Iowa
Research Interests:
Yoon Kyung’s research focuses on the development and application of empathetic AI, specifically in social robots, healthcare, and AI. She uses computational and quantitative methods (deep learning, NLP, and machine learning). Her work has been published in several venues, including CogSci, IEEE IROS, IEEE RO-MAN, AAAI HCOMP, and the Korean Journal of Cognitive Science.

Community Engagement:
Yoon Kyung has organized global and local workshops and meetups to help researchers and fellow graduate students exchange scientific findings and research methods.

This year, she is a co-organizer of 'Large Language Models in the RoMan Age: Exploring Social Impact and Implications for Design and Ethics' of the 2024 IEEE RO-MAN conference.

She is the first main organizer of the Seoul local meetup of the Cognitive Science Society (2022 and 2023). She has actively led various methodology workshops, including "Introduction to Prompt Engineering 101: Hands-on Workshop with Large Language Models" (Language model workshop for SNU graduate students) and Applied Cognition (AppCog) (a seminar for PhD students and industry researchers). She has also actively led graduate student-level journal club and tutorial sessions within the lab (Human Factors Psychology Lab).

Recent Publication 
  • Lee, YK., Suh, J., Zhan, H., Li, J.J., & Ong, D.C. (2024). Large Language Models Produce Responses Perceived to be Empathic. arXiv preprint. [pdf]
  • Zhan, H., Zheng, A., Lee, YK., Suh, J., Li, J.J., & Ong, D.C. (2024). Large Language Models are Capable of Offering Cognitive Reappraisal, if Guided. arXiv preprint. [pdf]
  • Bae, S., Lee, YK., Lee, J., Kim, J., Jeon, H., Lim, S., Kim, B., & Hahn, S. (2024). Enhancing Empathy in Virtual Reality: An Embodied Approach to Mindset Modulation. arXiv preprint. [pdf
  • Lee, YK., Lee, I., Shin, M., Bae, S., & Hahn, S. (2024). Enhancing Empathic Reasoning of Large Language Models Based on Psychotherapy Models for AI-assisted Social Support. Korean J of Cognitive Science (인지과학), 35(1), 23-48. [pdf]
  • Lee YK., Jung, Y., Kang, K., & Hahn, S. (2023). Developing Social Robots with Empathetic Non-Verbal Cues Using Large Language Models. Late Breaking Report for presentation at the 32nd IEEE International Conference on Robot and Human Interactive Communication (RO-MAN 2023). [pdf]

Full publication lists:
2024. 3. 31

[New Paper] Enhancing Empathic Reasoning of Large Language Models Based on Psychotherapy Models for AI-assisted Social Support

New paper published! We present a novel method, the Chain of Empathy (CoE) prompting, that utilizes insights from psychotherapy to induce LLMs to reason about human emotional states. This method is inspired by various psychotherapy approaches—Cognitive-Behavioral Therapy (CBT), Dialectical Behavior Therapy (DBT), Person-Centered Therapy (PCT), and Reality Therapy (RT)—each leading to different patterns of interpreting clients’ mental states. LLMs without CoE reasoning generated predominantly exploratory responses. However, when LLMs used CoE reasoning, we found a more comprehensive range of empathic responses aligned with each psychotherapy model’s different reasoning patterns. ...

Read More
2024. 4. 20

2024 IEEE RO-MAN WORKSHOP ACCEPTED: I am co-organizing, "Large Language Models in the RoMan Age: Exploring Social Impact and Implications for Design and Ethics" workshop

I'll co-organize a workshop to be held as part of the 2024 IEEE International Conference on Robot and Human Interactive Communication (RO-MAN), from August 26-30 in Pasadena, California, USA. We will have renowned panel speakers from various domains including human-robot interaction, psychology, robotics, and ethics, representing both academia and industry. The official workshop page will be released soon. Stay tuned!

Read More
2023. 11. 12

CoE prompt featured in a data science community

Exciting news—our Chain of Empathy Prompting was featured on a popular social media platform for data scientists. Thanks for the shout-out! We’re stoked to see people engaging with our work. Image credit: Raphaël MANSUY

Read More
2023. 2. 5

[New paper] Relationship Between Perspective-Taking Ability and Psychological and Emotional Characteristics Observed in a Large Emotion Diary Dataset: A Cluster Analysis

A new paper co-authored with my coworkers has just been published in the Korean Journal of Health Psychology!

Read More
2022. 8. 9

[Invited Talk] Scaling up Psychology: From Cognitive Psych to HAI

I was invited to introduce my research at the Connectome lab seminar. This talk will cover some of my previous work in the areas of natural language processing, big data, and artificial intelligence with empathy.

Read More
2022. 7. 19

CogSci 2022 Local Meetup @ Seoul! (Organizer: Yoon Kyung Lee)

This local meetup is in conjunction with CogSci 2022 to facilitate in-person networking and local community building, and to enhance the experience of the online CogSci 2022 conference.

Read More
2022. 1. 5

Mental Healthcare Chatbot Seminar

I led a workshop for graduate students and faculties on how to create a counseling chatbot using RASA, a machine learning and rule-based hybrid chatbot framework.

Read More

Yoon Kyung Lee Computational Affective and Social Cognition Lab, University of Texas at Austin & Human Factors Psychology Lab, Seoul National University (PhD candidate, ABD) www.yoonkyunglee.com | https://github.com/yoonlee78/