Scholar
Hyukhun Koh
Google Scholar ID: DJ690BMAAAAJ
SNU MILAB
Citations & Impact
Citations
61
H-index
5
i10-index
3
Publications
13
Co-authors
0
Publications
Resume (English only)
Academic Achievements
- Published multiple papers at top-tier venues including EMNLP, NAACL, NeurIPS, and SigDial, with several as first or co-first author
- Notable works: 'Harmful Prompt Laundering: Jailbreaking LLMs with Abductive Styles and Symbolic Encoding' (EMNLP 2025 Main), 'Conditional [MASK] Discrete Diffusion Language Model' (EMNLP 2025 Main), 'Generating Diverse Hypotheses for Inductive Reasoning' (NAACL 2025 Main & Oral)
- M.S. thesis received the 2024 Seoul National University IPAI Outstanding Dissertation Award
- Served as reviewer for ACL conferences (over 40 reviews from 2024–2025) and as Assistant Area Chair
- Invited reviewer for Elsevier’s 'Expert Systems With Applications'
Research Experience
- Project: 'Development of AI Technologies for Open-ended Alignment with Changing Environments and Values' (funded by ITRC)
- Project: 'Fairness and Safety of Large Language Models' (funded by NRF)
- Project: 'Process-Oriented Assessment AI for Customized Education' (funded by IITP)
- Project: 'Research on AI Technologies that Flexibly Evolve in Response to Strengthening Ethical Policies – Medical & Marketing' (funded by IITP)
- Participant in IITP Global Core Talent Development Program (Microsoft Research Asia - MSRA)
Co-authors