Scaling Creative Writing Beyond Story-Centric Data with Attribute-Guided Genre Expansion
Hwan Chang, Yongil Kim, Heuiyeen Yeen, Yireun Kim, Jinsik Lee, Hwanhee Lee^†
CIKM 2026
PDF

ChatInject: Abusing Chat Templates for Prompt Injection in LLM Agents
Hwan Chang^*, Yonghyun Jun^*, Hwanhee Lee^†
ICLR 2026
PDF| Code

Doc-PP: Document Policy Preservation Benchmark for Large Vision-Language Models
Haeun Jang^*, Hwan Chang^*, Hwanhee Lee^†
ACL 2026 Findings
PDF| Abstract| Code

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^†
AACL-IJCNLP 2026
PDF| Abstract

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
PDF| Abstract| Code

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)
PDF| Abstract| Code

Which Retain Set Matters for LLM Unlearning? A Case Study on Entity Unlearning
Hwan Chang, Hwanhee Lee^†
ACL 2025 Findings
PDF| Abstract

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
PDF| Abstract| Code

Leveraging Fine-grained Error Correction in Korean Speech Recognition for Consultation Services
Yonghyun Jun, Jimin Lee, Hwan Chang, Dongho Shin, Seolah Kim, Hwanhee Lee^†
Engineering Applications of Artificial Intelligence (EAAI)

EXAONE 4.5 Technical Report
LG AI Research
Technical Report, 2026
PDF| Abstract| Model

K-EXAONE Technical Report
LG AI Research
Technical Report, 2026
PDF| Abstract| Model