Curriculum Vitae

CV

Hoonick Lee · hoonick@korea.ac.kr · Seoul, South Korea · Data Mining and Information Systems (DMIS) Lab, Korea University

Research Interests

  • Biomedical and clinical NLP
  • Large language model systems for specialized domains
  • Natural-language interfaces to structured data (text-to-SQL, EHR)
  • Knowledge grounding and domain-aware reasoning
  • Evaluation and reliability of LLM behavior

Education

  • Integrated M.S./Ph.D. in Computer Science and Engineering

    Mar 2023 – Present

    Korea University

    • Data Mining and Information Systems (DMIS) Lab
    • Advisor: Prof. Jaewoo Kang
    • GPA 4.41 / 4.5

  • B.E. in Computer Science and Engineering (Dual Degree program)

    2022 – 2023

    Korea University

    • Second bachelor's program completed through Korea University's dual-degree curriculum, alongside Health and Environmental Science.

  • B.S. in Health and Environmental Science

    2016 – 2023

    Korea University, College of Health Science

    • Primary health-science training focused on radiological science.
    • Interdisciplinary major in Brain and Cognitive Sciences (B.E.), College of Informatics.
    • Hanryang Korean Archery Club — Vice President & Head of Training (2020–2022).

Publications

  1. [6]An LLM-based Chain-of-Response Counter-Scam System. Heedou Kim, Mogan Gim, Donghee Choi, Hoonick Lee, Soonil Bae, Mi-Young Kim, Jaewoo Kang. International Joint Conference on Artificial Intelligence (IJCAI), 2026. To appear.
  2. [5]Prompting Matters: Snippet-Aware Strategies for Biomedical QA with LLMs in BioASQ 13b. Hajung Kim*, Hoonick Lee*, Yewon Cho*, Jungwoo Park*, Jueon Park*, Soyon Park*, Yan Ting Chok*, Seungheun Baek*, Donghyeon Lee*, Jaewoo Kang. CLEF 2025 Working Notes, CEUR Workshop Proceedings, Vol. 4038, pp. 373–382, 2025. 1st place overall, BioASQ 13b Phase B (Exact Answers).
  3. [4]Culinary Class Wars: Evaluating LLMs Using ASH in Cuisine Transfer Task. Hoonick Lee, Mogan Gim, Donghee Choi, Jaewoo Kang. 2025 IEEE International Conference on Data Mining Workshops (ICDMW), CoGamy Workshop, pp. 657–660, 2025.
  4. [3]Analyzing Information Disparities across Modalities in Mortality Prediction. C. Kim, W. J. Yoon, H. Lee, J. O. Lee, M. Afshar, J. Kang, T. Miller. medRxiv, 2025.
  5. [2]Impact of High Pressure and Emotional Prompting Strategies on the Behavior of Large Language Models. M. Song, T. Lee, H. Hwang, Y. Park, C. Yoon, H. Lee, D. Kim, S. Park, J. Lee, et al.. Proceedings of the Korea Computer Congress (KCC), KIISE, pp. 910–912, 2025.
  6. [1]KU-DMIS at EHRSQL 2024: Generating SQL Query via Question Templatization in EHR. Hajung Kim, Chanhwi Kim, Hoonick Lee, Kyochul Jang, Jiwoo Lee, Kyungjae Lee, Gangwoo Kim, Jaewoo Kang. Proceedings of the 6th Clinical Natural Language Processing Workshop (NAACL 2024), pp. 672–686, 2024.

Research Experience & Shared Tasks

  • 1st place overall — BioASQ 13b Phase B (Exact Answers)

    2025

    KU-DMIS team · award received at CLEF 2025, Madrid

    • Biomedical question answering with exact answers: our snippet-aware prompting system ranked 1st, 1st, 2nd, and 1st across the four Phase B batches, securing the overall top position.

  • Workshop presentation — CoGamy @ IEEE ICDM 2025

    2025

    Washington, D.C.

    • Presented our work on evaluating culturally grounded creativity in LLM recipe generation, introducing the ASH (Authenticity, Sensitivity, Harmony) framework.

  • EHRSQL 2024 shared task — participant

    2024

    KU-DMIS team · Clinical NLP Workshop @ NAACL 2024

    • Built a question-templatization pipeline for reliable text-to-SQL over electronic health records, where incorrect SQL carries real clinical risk.

  • Lab Server Administrator, DMIS Lab

    Apr 2024 – Present

    Korea University

    • Keep the lab's GPU research infrastructure running: up to 24 multi-GPU servers at peak — from Titan X/Xp-era systems to RTX 3090 servers, DGX A100 systems, and RTX PRO 6000 Blackwell systems — plus RAID-based storage.

  • Graduate Researcher, DMIS Lab

    2023 – Present

    Korea University

    • Research on NLP and LLM systems for specialized domains — biomedical QA, clinical text-to-SQL, scam detection, and food computing — advised by Prof. Jaewoo Kang.

Certifications

  • Engineer Information Processing (정보처리기사) · HRD KoreaSep 2023
  • ADsP — Advanced Data Analytics Semi-Professional · Kdata (Korea Data Agency)Sep 2023
  • SQLD — SQL Developer · Kdata (Korea Data Agency)May 2022

Languages

  • Korean — Native
  • English — Fluent — TOEIC 985, TOEIC Speaking 180
  • Japanese — Intermediate (business communication)
  • Spanish — Elementary

Technical Skills

  • Programming: Python, SQL
  • Machine Learning & NLP: PyTorch, LLM systems and evaluation, Retrieval-augmented generation
  • Data: Relational databases, Electronic health records (MIMIC-style data)
  • Systems & Infrastructure: Linux multi-GPU server administration (up to 24 servers, Titan X/Xp through Blackwell generations), RAID-based storage management