Takyoung Kim

김탁영 (金卓映)

Hello, I am a Ph.D. Student in Conversational AI Lab at the University of Illinois Urbana-Champaign Computer Science, advised by Prof. Dilek Hakkani-Tür. Previously I received my Master's degree at Korea University, advised by Prof. Pilsung Kang.

My main research interest is focused on solving problems arising from human-machine communication in the real-world. I’m also interested in conversational reasoning (e.g., dialogue system and question answering), knowledge-intensive NLP (e.g., retrieving information), broad range of long-context modeling, and making language models trustworthy.

CV  /  Email  /  GitHub  /  Google Scholar  /  LinkedIn  /  X

profile photo

News

Education

University of Illinois Urbana-Champaign Aug 2024 - Present
Doctor of Philosophy, Computer Science

Korea University Sep 2020 - Aug 2022
Master of Engineering, Industrial Management Engineering

Sungkyunkwan University Mar 2013 - Aug 2020
Bachelor of Science in Engineering, Interdisciplinary Program of Convergent Software
Bachelor of Media & Communication

Work Experience

LG AI Research Apr 2023 - Mar 2024
Research Intern at Advanced Machine Learning Lab
Mentors: Kyungjae Lee, Moontae Lee

NAVER AI Lab Jul 2022 - Jan 2023
Research Intern at Language Research Team
Mentor: Sungdong Kim

Publications

(* = Equal Contribution)

Learning to Explore and Select for Coverage-Conditioned Retrieval-Augmented Generation


Takyoung Kim, Kyungjae Lee, Young Rok Jang, Ji Yong Cho, Gangwoo Kim, Minseok Cho, Moontae Lee
Preprint, 2024
link / code

Revealing User Familiarity Bias in Task-Oriented Dialogue via Interactive Evaluation


Takyoung Kim, Jamin Shin, Young-Ho Kim, Sanghwan Bae, Sungdong Kim
NLP4ConvAI Workshop at ACL (Oral, Best Paper Award), 2024
link / slide

DSTEA: Improving Dialogue State Tracking via Entity Adaptive Pre-training


Yukyung Lee, Takyoung Kim, Hoonsang Yoon, Pilsung Kang, Junseong Bang, Misuk Kim
Knowledge-Based Systems, 290:111542 (Q1, Impact Factor: 8.8), 2024
KnowledgeNLP Workshop at KDD, 2023
link

KoSBi: A Dataset for Mitigating Social Bias Risks Towards Safer Large Language Model Application


Hwaran Lee*, Seokhee Hong*, Joonsuk Park, Takyoung Kim, Gunhee Kim, Jung-Woo Ha
Proceedings of ACL (Industry Track), 2023
link / code

SQuARe: A Large-Scale Dataset of Sensitive Questions and Acceptable Responses Created Through Human-Machine Collaboration


Hwaran Lee*, Seokhee Hong*, Joonsuk Park, Takyoung Kim, Meeyoung Cha, Yejin Choi, Byoung Pil Kim, Gunhee Kim, Eun-Ju Lee, Yong Lim, Alice Oh, Sangchul Park, Jung-Woo Ha
Proceedings of ACL (Oral, Best Paper Nomination), 2023
link / code

Oh My Mistake!: Toward Realistic Dialogue State Tracking including Turnback Utterances


Takyoung Kim, Yukyung Lee, Hoonsang Yoon, Pilsung Kang, Junseong Bang, Misuk Kim
SereTOD Workshop at EMNLP, 2022
link

Mismatch between Multi-turn Dialogue and its Evaluation Metric in Dialogue State Tracking


Takyoung Kim, Hoonsang Yoon, Yukyung Lee, Pilsung Kang, Misuk Kim
Proceedings of ACL, 2022
link

Building an Integrated Framework of Korean Text Summarization and Text-to-Speech


Takyoung Kim, Jina Kim, Hyeongwon Kang, Subin Kim, Pilsung Kang
Journal of Korean Institute of Industrial Engineers, 48(1), 80-90, 2022
link / code / website




Takyoung Kim's Website