Jiwon Moon

I am a Ph.D. student at Seoul National University, advised by Prof. Kyomin Jung. My research interest is in the field of Natural Language Processing, especially about (i) Instruction Following and Instruction Hierarchy of Large Language Models, (ii) Agentic AI, and (iii) Bias and Robustness.

Education

Seoul National University (SNU), Seoul, Korea ^{2024.09-Present}

• Ph.D. Student in Artificial Intelligence (IPAI)
• Advisor: Prof. Kyomin Jung
• Machine Intelligence Lab (MILAB)

Seoul National University (SNU), Seoul, Korea ^{2017.03-2024.08}

• B.S. in Electrical and Computer Engineering

Publications

• Does Instruction Hierarchy Hold When Multiple Sources Conflict?
  Jiwon Moon*, Yerin Hwang*, Changho Lee, Taegwan Kang, Jinsik Lee, Honglak Lee, Kyomin Jung
  Under Review
• Language Shapes Instruction Hierarchy Compliance in Multilingual LLMs
  Jiwon Moon, Yerin Hwang, Kyomin Jung
  EMNLP 2026 Main [ Code ]
• How Instruction Hierarchy Breaks Under Pairwise Multi-Conflict Pressure
  Yerin Hwang, Jiwon Moon, Changho Lee, Kwangmin Ki, Taegwan Kang, Jinsik Lee, Honglak Lee, Kyomin Jung
  EMNLP 2026 Main
• Don't Judge Code by Its Cover: Exploring Biases in LLM Judges for Code Evaluation
  Jiwon Moon*, Yerin Hwang*, Dongryeol Lee, Taegwan Kang, Yongil Kim, Kyomin Jung
  EACL 2026 Findings
• Unplug and Play Language Models: Decomposing Experts in Language Models at Inference Time
  Nakyeong Yang, Jiwon Moon, Junseok Kim, Yunah Jang, Kyomin Jung
  CIKM 2025 (Oral)

Experience

LG AI Research, Seoul, Korea ^{2026.06-Present}

• Collaborative Researcher

Samsung Electronics, Suwon, Korea ^{2024.01-2024.02}

• Engineering Intern

Scholarships & Awards

• Creative and Independent AI Research Winner ^2026.06
• Creative and Independent AI Research Winner ^2025.05
• SNU IPAI Scholarship ^{2024.09-2026.08}