Gildong Hong
"The only way to do great research is to become obsessed with an interesting question."

Publications

Towards Interpretable Reasoning in Large Language Models.
G. Hong, C. Kim, Y. Park.
ACL 2025.
Robust Fine-tuning via Gradient Projection for NLP.
G. Hong, M. Lee, C. Kim.
NeurIPS 2024.
A Survey on Mechanistic Interpretability.
G. Hong, C. Kim.
TMLR 2024.
Understanding Spurious Correlations in Text Classification.
G. Hong, J. Choi, C. Kim.
EMNLP 2023.
On the Robustness of Pre-trained Language Models under Distribution Shift.
G. Hong, C. Kim.
NAACL 2022.
Navigate
About Me
Publications
Writing
Email
Links
Google Scholar
GitHub
Hankook NLP Lab
KO

Visitor # 003847
Last updated March 2026. Best viewed at 800x600.