Hwan Chang
M.S. Student at Chung-Ang University
location_on Seoul, Koreaemail hwanchang16@gmail.com
Google Scholar
Github
X
insert_drive_file CV
I am a M.S. student in Department of AI at Chung-Ang University, Seoul, Korea.
News
Jan. 2026: Our ChatInject has been accepted to ICLR 2026.
Dec. 2025: Our K-EXAONE has been released! (Model, Technical Report)
Sep. 2025: I will be joining the EXAONE Lab at LG AI Research as a Research Intern.
Aug. 2025: Two of our works (CoPriva, OCR Head (Oral)) have been accepted at EMNLP 2025.
Publications
-
ChatInject: Abusing Chat Templates for Prompt Injection in LLM Agents,
Hwan Chang*, Yonghyun Jun*, Hwanhee Lee✝
ICLR 2026 -
K-EXAONE Technical Report,
LG AI Research (..., Hwan Chang, ...)
Technical Report, 2026 -
Keep Security! Benchmarking Security Policy Preservation in Large Language Model Contexts Against
Indirect Attacks in Question Answering,
Hwan Chang*, Yumin Kim*, Yonghyun Jun, Hwanhee Lee✝
EMNLP 2025 -
How Do Large Vision-Language Models See Text in Image? Unveiling the Distinctive Role of OCR
Heads,
Ingeol Baek, Hwan Chang, Sunghyun Ryu, Hwanhee Lee✝
EMNLP 2025 (Oral) -
Which Retain Set Matters for LLM Unlearning? A Case Study on Entity Unlearning,
Hwan Chang, Hwanhee Lee✝
ACL 2025 Findings -
Probing-RAG: Self-Probing to Guide Language Models in Selective Document Retrieval,
Ingeol Baek, Hwan Chang, Byeongjeong Kim, Jimin Lee, Hwanhee Lee✝
NAACL 2025 Findings -
Doc-PP: Document Policy Preservation Benchmark for Large Vision-Language Models,
Haeun Jang*, Hwan Chang*, Hwanhee Lee✝
Arxiv, 2026 -
Hallucinate at the Last in Long Response Generation: A Case Study on Long Document Summarization,
Joonho Yang, Seunghyun Yoon, Hwan Chang, Byeongjeong Kim, Hwanhee Lee✝
Arxiv, 2025 -
Leveraging Fine-grained Error Correction in Korean Speech Recognition for Consultation Services,
Yonghyun Jun, Jimin Lee, Hwan Chang, Dongho Shin, Seolah Kim, Hwanhee Lee✝
2025
Selected
Preprints
Work Experience
-
LG AI Research Seoul, KoreaResearch Intern @ EXAONE LabSep 2025 - Dec 2025
Education
Chung-Ang University, Seoul, Korea Sep.2024 - Aug.2026- M.S. in Department of Artificial Intelligence
- Advisor: Prof. Hwanhee Lee
- B.S. in Computer Science and Engineering
Academic Services
- Reviewer: ACL 2026, EMNLP 2025, AAAI 2026, EACL 2026
Teaching Experience
-
Object-Oriented Programming
Spring 2025 -
Artificial Intelligence Design
Fall 2024
Research Projects
- Improvement of Speech Recognition Rate Using LLMs (Seoul 120 Dasan Call Center) Detecting and Correcting Errors of ASR System for Dialogue Data with Large Language Models