Profile Photo

Cheongwoong Kang

Ph.D. Candidate
Statistical Artificial Intelligence Lab
KAIST
cw.kang@kaist.ac.kr
[CV] [Google Scholar] [GitHub] [LinkedIn]

I am a Ph.D. candidate at the Graduate School of AI, KAIST, affiliated with the SAIL (advisor: Jaesik Choi). My research focuses on natural language processing (NLP) and explainable AI (XAI), with two main directions: (1) understanding how knowledge is encoded, processed, and utilized in language models, including how it is retrieved and extracted; and (2) investigating how that knowledge can be modified or augmented.

Publications and Preprints

An up-to-date list is available on my Google Scholar.

2026
Decision Path Tracing for Causal Analysis in Transformers
Won Jo, Dahee Kwon, Jongeun Baek, Cheongwoong Kang and Jaesik Choi
NeurIPS 2026
[paper]
Beyond Paraphrases: Generalization Across Task Formats in Parametric Knowledge Editing
Cheongwoong Kang, Jongeun Baek, Yeonjea Kim and Jaesik Choi
EMNLP 2026 Findings
[paper]
K-MetBench: A Multi-Dimensional Benchmark for Fine-Grained Evaluation of Expert Reasoning, Locality, and Multimodality in Meteorology
Soyeon Kim, Cheongwoong Kang, Myeongjin Lee, Eun-Chul Chang, Jaedeok Lee and Jaesik Choi
ACL 2026 Findings
[paper]
2025
When Format Changes Meaning: Investigating Semantic Inconsistency of Large Language Models
Cheongwoong Kang, Jongeun Baek, Yeonjea Kim and Jaesik Choi
EMNLP 2025 Findings
[paper] [code] [poster] [slides]
Neural ODE Transformers: Analyzing Internal Dynamics and Adaptive Fine-tuning
Anh Tong, Thanh Nguyen-Tang, Dongeun Lee, Duc Nguyen, Toan Tran, David Leo Wright Hall, Cheongwoong Kang and Jaesik Choi
ICLR 2025
[paper]
2024
Balanced Domain Randomization for Safe Reinforcement Learning
Cheongwoong Kang, Wonjoon Chang and Jaesik Choi
Applied Sciences
[paper] [code]
2023
Impact of Co-occurrence on Factual Knowledge of Large Language Models
Cheongwoong Kang and Jaesik Choi
EMNLP 2023 Findings
[paper] [code] [poster] [slides]
2022
Why Do Neural Language Models Still Need Commonsense Knowledge to Handle Semantic Variations in Question Answering?
Sunjae Kwon, Cheongwoong Kang, Jiyeon Han and Jaesik Choi
Preprint
[paper] [code]
2021
Cooperative Multi-Robot Task Allocation with Reinforcement Learning
Bumjin Park, Cheongwoong Kang and Jaesik Choi
Applied Sciences
[paper]
Scheduling PID Attitude and Position Control Frequencies for Time-Optimal Quadrotor Waypoint Tracking under Unknown External Disturbances
Cheongwoong Kang, Bumjin Park and Jaesik Choi
Sensors
[paper]
2020
Why Do Masked Neural Language Models Still Need Common Sense Knowledge?
Sunjae Kwon, Cheongwoong Kang, Jiyeon Han and Jaesik Choi
Reasoning for Complex QA Workshop @ AAAI 2020
[paper]
2018
Symbolizing Numbers to Improve Neural Machine Translation
Cheongwoong Kang, Youngheon Ro, Jisu Kim and Heeyoul Choi
Journal of Digital Contents Society
[paper]