Hi! or "Annyeonghaseyo!" I am a M.S. student in the Computer Science & Engineering Department at the Korea University and a member of Data Mining and Information Systems (DMIS) Lab, advised by Prof. Jaewoo Kang. I worked as an AI researcher at Nara-Information for seven months, and had an experience of Lab researcher in Song Lab (hosted by Prof. Sanghoun Song). Prior to my M.S. studies, I received a Bachelor's degree in Linguistics and Computer Science from Korea University.

My research area covers the broad field of natural language processing, with a focus on Post-Training, Mechanistic Interpretability, and Retrieval Augmented Generation. My goal is to broaden the interpretability approach to practical alignment problems such as Safety, Knowledge Editing, and Reasoning. I am also interested in domain-specific language models, including Biomedical LM.

You can find my CV in here.

Yein Park

[jɛin bɑk]

Email : parkyein522 [at] gmail [dot] com / 522yein [at] korea [dot] ac [dot] kr
#NLP #PT #Interpret #RAG

Selected Publications

Work Experience

Aigen Science Inc.
[Sep 2025 - FEB 2026] @South Korea

Research Intern Advisor: Sanghoon Lee
- Developed on-premise clinical multi-agent system for diabetes management to assist medical experts.
- Building small expert LLMs for real-world prescribing scenarios with GDPO-based search RL.

Nara Information
[AUG 2023 - FEB 2024] @South Korea

Research Intern Metaverse lab team
- Designed domain specific sLLM for local government
- Develped tour recommendation system combined with LLM by RAG method
- Assisted Korean curtural contents project using commercial AI systems.

Song Lab(Lingustics Lab), Korea Univ.
[May 2022 - FEB 2023] @South Korea

Researcher Korean AI dataset team (host: Prof. Sanghoun Song)
- Joined Korean legal/bidomedical AI dataset project.
- Worked as crowdworker for legal data tagging and labelling.

Education

M.S. in Computer Science & Engineering at Korea University
[2024 - present]

Data Mining & Information Systems Lab (advisor: Prof. Jaewoo Kang)

B.S. in Linguistics/Computer Science & Engineering at Korea University
[2017 - 2024]

(advisor: Prof. Seok-Hoon You)

Projects

Interpretability Inspired Alignment and Post-Training
[2025 - present]

- Safety Training Methods using Transformer Circuits.
- Differentiate Specific Emergent Attention Heads using Transforemr Circuits.

Temporal Alignment for Large Language Models
[2025 - present]

- Temporal Alignment through Chronosemanticity.

Research on Knowledge Distillation Method
[2024 - 2025]

- Supported to research on knowledge distillation method.
- Utilize Knowledge Hierarchy.

Development of Korean local tour recommendation system
[2023 - 2024]

- Developed Korean local tour recommendation system combined with LLM by RAG methods.
- Designed pipeline of recommendation using personalized tour data, with efficient ML methods.
- [Available GPTs ver]
- [link to the post]

Development of domain specific sLLM for local government
[2023 - 2023]

- Developed sLLM specialized to administrative and civil affairs works for local government's officers.
- Developed summarization and search agents among the entire LLM pipeline.
- [link to the post]

Honors and Scholarships

First Place Winner of MedHopQA-2025
[Aug 2025]
Research Scholarship for Research Asistant ($6000)
[Sep 2024 - Feb 2025]
Dean's List
[Spring 2021]
Semester High Honors
[2017 - 2021]
The scholarship amounts shown above are approximate.

Academic Activities

[Reviewer] ACL 2026
[Feb 2026]

- The 64rd Annual Meeting of the Association for Computational Linguistics
- Participated as a secondary reviewer

[Reviewer] EMNLP 2025
[Jun 2025]

- The 2025 Conference on Empirical Methods in Natural Language Processing
- Participated as a secondary reviewer

[Reviewer] ACL 2025
[Apr 2025]

- The 63rd Annual Meeting of the Association for Computational Linguistics
- Participated as a secondary reviewer