Cheongwoong Kang

Email / GitHub / Google Scholar / LinkedIn / CV

I am currently pursuing my PhD at the Graduate School of AI, KAIST, affiliated with the SAIL. My PhD advisor is Jaesik Choi. I am interested in natural language processing, deep learning, reinforcement learning and explainable AI (XAI). My primary interest lies in how knowledge is encoded and processed for reasoning in language models, along with how knowledge can be extracted. I am actively engaged in two research directions: (1) analyzing knowledge inside language models and (2) improving language models by controlling or augmenting knowledge.

selected publications

Impact of Co-occurrence on Factual Knowledge of Large Language Models

Cheongwoong Kang, and Jaesik Choi

In Findings of the Association for Computational Linguistics: EMNLP, 2023

Bib PDF Code Poster Slides Website

@inproceedings{kang2023impact,
  title = {Impact of Co-occurrence on Factual Knowledge of Large Language Models},
  author = {Kang, Cheongwoong and Choi, Jaesik},
  booktitle = {Findings of the Association for Computational Linguistics: EMNLP},
  year = {2023},
}