Scholar
Cheongwoong Kang
Google Scholar ID: MYiAPWYAAAAJ
KAIST
Citations & Impact
Citations
132
H-index
5
i10-index
4
Publications
8
Co-authors
7
list available
Resume (English only)
Academic Achievements
- Published multiple papers, including 'When Format Changes Meaning: Investigating Semantic Inconsistency of Large Language Models' (EMNLP 2025 Findings), 'Neural ODE Transformers: Analyzing Internal Dynamics and Adaptive Fine-tuning' (ICLR 2025), 'Balanced Domain Randomization for Safe Reinforcement Learning' (Applied Sciences, 2024), 'Impact of Co-occurrence on Factual Knowledge of Large Language Models' (EMNLP 2023 Findings), and more.
Research Experience
- Conducts research at the Statistical Artificial Intelligence Lab (SAIL) at KAIST, focusing on natural language processing and explainable AI.
Education
- Ph.D. candidate at the Graduate School of AI, KAIST, advisor: Jaesik Choi, affiliated with the Statistical Artificial Intelligence Lab (SAIL).
Background
- Research interests: natural language processing (NLP) and explainable AI (XAI), with a particular interest in how knowledge is encoded, processed, and utilized for reasoning in language models, as well as how it can be effectively extracted. Work spans two key directions: (1) analyzing the internal knowledge representations and mechanisms of language models, and (2) enhancing models by controlling or augmenting knowledge.
Miscellany
- Links to CV, Google Scholar, GitHub, and LinkedIn are available on the personal website.
