Hyojun Choi

Research Interests

• Large Language Models
  Data Generation / Reasoning Model / Evaluation
• Knowledge Alignment
  Knowledge Augmented Language Model / Knowledge Embedding / Knowledge Validation
• Responsible AI
  Interpretable AI / Safety Alignment

Education & Experience

• Yonsei University, Seoul, South Korea
  Ph.D Student (Integrated Course) in Artificial Intelligence
  2023.09 – Present
• Yonsei University, Seoul, South Korea
  B.S. in Integrated Technology
  2020.03 – 2023.02
• Google Machine Learning Bootcamp Korea 2022 (3rd Season)
  Machine Learning Bootcamp
  2022.06 – 2022.09

Publications

• VSPO: Validating Semantic Pitfalls in Ontology via LLM-based CQ Generation
  Hyojun Choi*, Seokju Hwang, Kyong-Ho Lee
  AAAI Oral, 2026
  LLM-based competency question generation for validating misalignment between symbolic definitions and concept descriptions.

• OmEGa (Ω): Ontology-based information extraction framework for constructing task-centric knowledge graph from manufacturing documents with large language model
  Midan Shim, Hyojun Choi, Heeyeon Koo, Kaehyun Um, Kyong-Ho Lee, Sanghyun Lee
  Advanced Engineering Informatics, 2025
  Develop OmEGa, an Ontology-based Information Extraction Framework for Task-Centric Knowledge Graphs.