Jeonghwan Kim
Ph.D. Student, BLENDER Lab, UIUC
jk100 [AT] illinois.edu
About
Ph.D. student at BLENDER Lab at University of Illinois, Urbana-Champaign (UIUC), currently advised by Professor Heng Ji
I obtained my Master's from the School of Computing, KAIST, where I was advised by Prof. Sung-Hyon Myaeng.
My primary research interests lie in the intersection of natural language processing (NLP) and machine learning. As an NLP researcher, I want to build next-generation language models that are capable of dealing with the interplay of general and domain-specific knowledge; these models, hopefully, will serve to empower individuals in their daily effort to acquire new knowledge.
I'm particularly interested in developing neuro-symbolic language models that can process symbols that possess certain symbol-specific characteristics (e.g., numbers, graphs) and understand those symbols in the light of peripheral context and external knowledge.
Here are some keywords about my research interests:
- Question Answering (QA)
- Language Modeling
- Retrieval-Augmented LMs
- Neuro-symbolic LMs
Education
University of Illinois, Urbana-Champaign (UIUC) Aug. 2023 - Present
Ph.D. in Computer Science
Korea Advanced Institute of Science and Technology (KAIST) Feb. 2020 - Feb. 2022
M.S. in School of Computing
Handong Global University Mar. 2014 - Feb. 2020
B.S. in Computer Science & Electrical Engineering (Magna Cum Laude)
Publications
* indicates equal contribution.
Finer: Investigating and Enhancing Fine-Grained Visual Concept Recognition in Large Vision Language Models
Jeonghwan Kim, Heng Ji
Preprint
Why So Gullible? Enhancing the Robustness of Retrieval-Augmented Models against Counterfactual Noise
Giwon Hong*, Jeonghwan Kim*, Junmo Kang*, Sung-Hyon Myaeng, Joyce Jiyoung Whang
NAACL 2024, Findings
FinePrompt: Unveiling the Role of Finetuned Inductive Bias on Compositional Reasoning in GPT-4
Jeonghwan Kim*, Giwon Hong*, Sung-Hyon Myaeng, Joyce Jiyoung Whang
EMNLP 2023, Findings
Graph-Induced Transformers for Efficient Multi-Hop Question Answering
Giwon Hong, Jeonghwan Kim, Junmo Kang, Sung-Hyon Myaeng
EMNLP 2022
Exploiting Numerical-Contextual Knowledge to Improve Numerical Reasoning in Question Answering
Jeonghwan Kim, Junmo Kang, Giwon Hong, Kyung-min Kim, Sung-Hyon Myaeng
NAACL 2022, Findings
Leveraging Order-Free Tag Relations for Context-Aware Recommendation
Junmo Kang, Jeonghwan Kim, Suwon Shin, Sung-Hyon Myaeng
EMNLP 2021
Have You Seen That Number? Investigating Extrapolation in Question Answering Models
Jeonghwan Kim, Giwon Hong, Kyung-min Kim, Junmo Kang, Sung-Hyon Myaeng
EMNLP 2021
Can You Distinguish Truthful from Fake Reviews? User Analysis and Assistance Tool for Fake Review Detection
Jeonghwan Kim*, Junmo Kang*, Suwon Shin*, Sung-Hyon Myaeng
HCI+NLP | EACL 2021
Maximizing Efficiency of Language Model Pre-training for Learning Representation
Junmo Kang*, Suwon Shin*, Jeonghwan Kim*, Jaeyoung Jo*, Sung-Hyon Myaeng
arXiv 2020
Object Classification on raw radar data using convolutional neural networks
Heejae Han, Jeonghwan Kim, Junyoung Park, YuJin Lee, Hyunwoo Jo, Yonghyeon Park, Eric T Matson, Seongha Park
IEEE Sensors Applications Symposium (SAS), 2019
Towards the development and realization of an undetectable stealth UAV
Jiyeon Oh, Daeun Choe, Chanhui Yun, Jeonghwan Kim, Michael Hopmeier
Third IEEE International Conference on Robotic Computing, 2019
Autonomous Parking Simulator for Reinforcement Learning
Hayoung Eom, Jeonghwan Kim, Seungyun Ji, Heeyoul Choi
Journal of Digital Contents Society
Vitæ
Full CV in PDF.
-
University of Illinois Urbana-Champaign Aug. 2023 - PresentPh.D. in Computer Science
BLENDER Lab -
KAIST IR&NLP Lab Mar. 2022 - PresentResearch Associate
Working on QA and Graph Networks -
KAIST Feb. 2020 - Feb. 2022M.Sc. in School of Computing
IR&NLP Lab -
Republic of Korea Marine Corps Mar. 2015 - Dec. 2016Honorably discharged as Sergeant
Mandatory Military Service -
Handong Global University Mar. 2014 - Feb. 2020B.Sc. in Computer Science & Electrical Engineering
Magna Cum Laude