About Me
I am a Postdoctoral Researcher at the University of Luxembourg, affiliated with the Software Verification and Validation (SVV) group at the Interdisciplinary Centre for Security, Reliability and Trust (SnT). I work with Prof. Domenico Bianculli on research at the intersection of NLP/NLU, Requirements Engineering, and financial and regulatory document analysis.
I received my Ph.D. in Artificial Intelligence from Yonsei University, where I was a member of the Theory of Computation (ToC) Lab under the supervision of Prof. Yo-Sub Han.
My current postdoctoral work focuses on an EIB-collaborative project that applies NLP, NLU, and Requirements Engineering techniques to problems in the financial and regulatory domains, including the analysis of financial contracts and legal documents.
My broader research aims to enhance the safety, transparency, and interpretability of large language models (LLMs) through detection, watermarking, and attribution techniques. Specifically, I investigate three complementary directions:
- Linguistic and stylistic feature–based detection, which distinguishes human- and LLM-generated text or code by analyzing subtle differences in writing patterns;
- LLM watermarking, which embeds imperceptible signals into generated outputs to enable reliable provenance tracing; and
- Domain-specific NLP/NLU and Requirements Engineering, which supports the analysis, structuring, and verification of complex financial, legal, and regulatory documents.
I have developed multi-modal and multi-lingual systems for detecting and watermarking AI-generated content across natural language and source code in English, Korean, Python, C, C++, and Java.
More broadly, I am deeply interested in AI safety, responsible AI, interpretable model design, and trustworthy NLP systems for high-stakes domains.
Research Interests
- Detection of LLM-Generated Text/Code using Linguistic/Stylistic Features
- LLM Watermarking for LLM-Generated Text/Code Attribution and Provenance
- NLP/NLU for Financial, Legal, and Regulatory Documents
- Requirements Engineering for Domain-Specific Document Analysis
- Human-Centered NLP
- Linguistics + AI, especially Korean and multilingual settings
- Responsible, Interpretable, and Trustworthy AI
Recent News
- [Jun 2026] New preprint LUNA-"Linguistics-Aware Non-Distortionary LLM Watermarking" is now available on arXiv.
- [Jun 2026] I started as a Postdoctoral Researcher in the Software Verification and Validation (SVV) group at the University of Luxembourg, SnT, working with Prof. Domenico Bianculli on NLP/NLU and Requirements Engineering for financial and regulatory documents.
- [Apr 2026] My LLM Watermarking paper ("A Linguistics-Aware LLM Watermarking via Syntactic Predictability") has been accepted to ACL 2026 Main Conference!
- [Mar 2026] Continuing service as a reviewer for ACL Rolling Review (ARR) and invited as a reviewer for the ACL 2026 Student Research Workshop (SRW).
- [Jan 2026] New preprint LREAD-"From Intuition to Calibrated Judgment: A Rubric-Based Expert-Panel Study of Human Detection of LLM-Generated Korean Text" is now available on arXiv.
- [Jan 2026] Presented WaterMod (LLM Watermarking Framework) at AAAI 2026 Main Track (Oral Presentation) in Singapore.
- [Jan 2026] Two LLM watermarking papers have been accepted to EACL 2026 (Main and Findings).
- [Nov 2025] My first LLM watermarking paper (WaterMod) has been accepted to AAAI 2026 Main Technical Track (Oral Presentation)!
- [Oct 2025] New preprint STELA-"A Linguistics-Aware LLM Watermarking via Syntactic Predictability" is now available on arXiv.
- [Sep 2025] Paper accepted to Engineering Applications of Artificial Intelligence. Detector for LLM-paraphrased code.
- [Aug 2025] Two papers accepted to EMNLP 2025 (Main and Findings).
- [Aug 2025] Presented KatFishNet (LLM-generated Korean text detector) at ACL 2025 (Main) in Vienna, Austria.