Keep Security! Benchmarking Security Policy Preservation in Large Language Model Contexts Against Indirect Attacks in Question Answering
Hwan Chang*, Yumin Kim*, YongHyeon Jun, Hwanhee Lee✝
EMNLP 2025 (main)

ChatInject: Abusing Chat Templates for Prompt Injection in LLM Agents
Hwan Chang*, Yonghyun Jun*, Hwanhee Lee✝
arXiv preprint (2509.22830)

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 (main)

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 preprint (2505.15291)

Fine-grained Error Correction in Korean Speech Recognition for Consultation Services
Yonghyun Jun, Jimin Lee, Hwan Chang, Dongho Shin, Seolah Kim , Hwanhee Lee✝
Under Review

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)

대체 상상을 통한 초거대 언어모델 언러닝

Hwan Chang, Hwanhee Lee

대한전자공학회 하계종합학술대회 2024