Yonghyun Jun

I am a Master's Student in Department of AI at Chung-Ang University, Seoul, Korea, advised by Prof. Hwanhee Lee at the Language Intelligence Lab (LILAB). My Research Interest is in the field of Natural Language Processing, especially about (i) Language Model Personalization, (ii) Dialogue and Interaction Systems, (iii) Agent Safety, and (iv) Sentiment Analysis.

Education

Chung-Ang University, Seoul, Korea ^{Mar. 2025 - Current}

• M.S. in Artificial Intelligence
• Advisor: Prof. Hwanhee Lee

Chung-Ang University, Seoul, Korea ^{Mar. 2021 - Feb. 2025}

• B.S. in Artificial Intelligence
• GPA: 4.2 / 4.5 (Major GPA: 4.38 / 4.5)

Publications

• ChatInject: Abusing Chat Templates for Prompt Injection in LLM Agents,
  Hwan Chang*, Yonghyun Jun*, Hwanhee Lee✝
  ICLR 2026 [Code]
• Exploring Persona Sentiment Sensitivity in Personalized Dialogue Generation,
  Yonghyun Jun, Hwanhee Lee✝
  ACL 2025 [Code] [Slide] [Poster]
• Dynamic Order Template Prediction for Generative Aspect-Based Sentiment Analysis,
  Yonghyun Jun, Hwanhee Lee✝
  ACL 2025 [Code] [Slide] [Poster]
• 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

Preprints / Under Review

• Identifying and Mitigating Bottlenecks in Role-Playing Agents: A Systematic Study of Disentangling Character Profile Axes,
  Yonghyun Jun*, Junhyuk Choi*, Jihyeong Park, Jeonghyun Park, Liu Nicole Geumheon, Hwanhee Lee✝
  arXiv Preprint / Under Review
• Leveraging 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

Scholarships & Awards

• Graduate Research Scholarship (GRS) (Full tuition) ^{Mar. 2025 ~ Current}
• Graduated with Highest Honors (GPA ≥ 4.2/4.5) ^{Feb. 2025}
• Leadership Scholarship (Department Representative) ^{Nov. 2023}
• Excellence Award at 2022 SW·AI Startup Idea Competition ^{Sep. 2022}
• Departmental Merit Scholarship (1st in Cohort) ^{Sep. 2022}

Research Projects

• Plug-in External-Memory Models for Augmenting Knowledge of Large Language Models
  Research on Next‑generation RAG via Plugging‑in External Model Memory
• Next-Generation O2O Fashion Retail System: Enhancing Sales Through Integration of Personal Shoppers and Immersive Virtual Fitting
  Developing Personalized Fashion Recommendation System, Served as Institutional PI
• Improvement of Speech Recognition Rate Using Language Models
  Detecting and Correcting Errors of Dialogue Transcriptions with Language Models