DongGeon Lee
M.S. Student, POSTECH
Graduate School of Artificial Intelligence
dg.lee [AT] postech.ac.kr
About
I'm DongGeon Lee, an AI safety researcher pursuing my M.S. at the Graduate School of Artificial Intelligence, Pohang University of Science and Technology (POSTECH), under the guidance of Prof. Hwanjo Yu. I earned my B.S. from Inha University, South Korea.
I aim to make a positive impact by building safer, more reliable AI with data and LLMs. My research focuses on data-centric NLP and LLM safety, including evaluations, guardrails, and automated red teaming. I’m open to collaborations on responsible AI across academia and industry.
News
- [Oct. 2025] Our paper won the Excellent Paper Award from HCLT 2025!
- [Aug. 2025] One paper is accepted at EMNLP 2025! See you in Suzhou 🇨🇳.
- [Jun. 2025] I will be a Student Volunteer at ACL 2025! See you in Vienna 🇦🇹.
- [Jan. 2025] I'm spending this winter as a research intern at KT!
- [Oct. 2024] Our paper won the Excellent Paper Award from HCLT 2024!
- [Oct. 2024] I won the gold prize in the Korean AI Language Proficiency Challenge held by the NIKL 🇰🇷! [News (Kor.)]
- [Feb. 2024] I got admitted at POSTECH GSAI as an M.S. student.
- [Feb. 2024] I received the Top Engineering Student Award from Inha University!
Education
Pohang University of Science and Technology (POSTECH)Feb. 2024 - Present
M.S. in Artificial Intelligence
(Advisor: Prof. Hwanjo Yu)
Inha UniversityMar. 2018 - Feb. 2024
B.S. in Information & Communication Engineering
Publications
( * Equal contribution; † Corresponding author )
COMPASS: A Framework for Evaluating Organization-Specific Policy Alignment in LLMs
Dasol Choi*, DongGeon Lee*, Brigitta Jesica Kartono*, Helena Berndt, Haon Park, Hwanjo Yu†, Minsuk Kahng†
Under Review
Are Vision-Language Models Safe in the Wild? A Meme-Based Benchmark Study
DongGeon Lee*, Joonwon Jang*, Jihae Jeong, Hwanjo Yu
EMNLP 2025 Main
When Good Sounds Go Adversarial: Jailbreaking Audio-Language Models with Benign Inputs
Bodam Kim*, Hiskias Dingeto*, Taeyoun Kwon*, Dasol Choi, DongGeon Lee, Haon Park, JaeHoon Lee, Jongho Shin
Preprint
REFIND at SemEval-2025 Task 3: Retrieval-Augmented Factuality Hallucination Detection in Large Language Models
DongGeon Lee, Hwanjo Yu
SemEval @ ACL 2025
COMPASS: A Framework for Evaluating Organization-Specific Policy Alignment in LLMs
Dasol Choi*, DongGeon Lee*, Brigitta Jesica Kartono*, Helena Berndt, Haon Park, Hwanjo Yu†, Minsuk Kahng†
Under Review
Are Vision-Language Models Safe in the Wild? A Meme-Based Benchmark Study
DongGeon Lee*, Joonwon Jang*, Jihae Jeong, Hwanjo Yu
EMNLP 2025 Main
Everyday Physics in Korean Contexts: A Culturally Grounded Physical Reasoning Benchmark
Jihae Jeong*, DaeYeop Lee*, DongGeon Lee, Hwanjo Yu
MRL @ EMNLP 2025
Global PIQA: Evaluating Physical Commonsense Reasoning Across 100+ Languages and Cultures
Tyler A. Chang*, Catherine Arnett*, ..., DongGeon Lee, ... (339 authors; author list abbreviated)
Preprint
Synthesizing a Korean-centric Math Corpus to Enhance Math Problem-Solving Ability in Korean Large Language Models
DongGeon Lee*, Jisoo Baik, Wonjae Park, Hwanjo Yu
HCLT 2025 (Domestic)
When Good Sounds Go Adversarial: Jailbreaking Audio-Language Models with Benign Inputs
Bodam Kim*, Hiskias Dingeto*, Taeyoun Kwon*, Dasol Choi, DongGeon Lee, Haon Park, JaeHoon Lee, Jongho Shin
Preprint
Typed-RAG: Type-Aware Decomposition of Non-Factoid Questions for Retrieval-Augmented Generation
DongGeon Lee*, Ahjeong Park*, Hyeri Lee, Hyeonseo Nam, Yunho Maeng
XLLM @ ACL 2025 | NAACL 2025 SRW (Non-Archival)
REFIND at SemEval-2025 Task 3: Retrieval-Augmented Factuality Hallucination Detection in Large Language Models
DongGeon Lee, Hwanjo Yu
SemEval @ ACL 2025
Theme-Explanation Structure for Table Summarization using Large Language Models: A Case Study on Korean Tabular Data
TaeYoon Kwack*, Jisoo Kim*, Ki Yong Jung, DongGeon Lee, Heesun Park
TRL @ ACL 2025
Designing Synthetic Data and Training Strategies for Multi-hop Retrieval-Augmented Generation
Kyumin Lee, Minjin Jeon, Sanghwan Jang, DongGeon Lee, Hwanjo Yu
KCC 2025 (Domestic)
Enhancing Adverse Event Reporting with Clinical Language Models: Inpatient Falls
Insook Cho, Hyunchul Park, Byeong Sun Park, DongGeon Lee
Journal of Advanced Nursing (SCIE, IF: 3.8, Q1; 97.2%)
Question Types Matter: An Analysis of Question-Answering Performance in Retrieval-Augmented Generation Across Diverse Question Types
DongGeon Lee*, Ahjeong Park*, Hyeri Lee, Hyeonseo Nam, Yunho Maeng
HCLT-KACL 2024 (Domestic)
Tabular-TX: Theme-Explanation Structure-based Table Summarization via In-Context Learning
TaeYoon Kwack*, Jisoo Kim*, Ki Yong Jung, DongGeon Lee, Heesun Park
HCLT-KACL 2024 (Domestic); Excellent Paper Award
Effects of Language Differences on Inpatient Fall Detection Using Deep Learning
Insook Cho, EunJu Lee, DongGeon Lee
MedInfo 2023
Bridging the Reporting Gap of Inpatient Falls to Improve Safety Practices Using Deep-Learning-Based Language Models and Multisite Data
DongGeon Lee, EunJu Lee, Insook Cho
AMIA CIC 2023
Through deep learning-based video processing, Design and implementation of Smart Port Parking Information System
Changhun Koo*, Yoonjoo Jung*, DongGeon Lee*
ACK 2021 (Domestic)
Vitæ
Full CV in PDF.
-
POSTECH Feb. 2024 - PresentM.S. Student in Artificial Intelligence
DI Lab (Advisor: Prof. Hwanjo Yu) -
AIM Intelligence Jul. 2025 - PresentResearch Scientist
-
KT Corporation Jan. 2025 - Feb. 2025Research Intern
Language AI Team -
Inha University Mar. 2018 - Feb. 2024B.S. in Information & Communication Engineering