Research
Research Focus
- Semantic Embedding & Retrieval: Scientific, industrial, domain-specialized corpora를 위한 dense retrievers를 학습하고 평가합니다.
- Reasoning Signals & Efficiency: Reasoning quality를 유지하면서 inference와 training을 효율화하기 위한 reward signals, rationale reduction, decoding strategies를 연구합니다.
- Trustworthy LLM Systems: Finance, manufacturing, insurance 같은 regulated domain에 맞는 privacy-aware, repeatable evaluation 및 deployment pipelines를 만듭니다.
Data Science and Business Analytics Lab
저는 Data Science and Business Analytics Lab의 구성원이며, Prof. Pilsung Kang의 지도를 받고 있습니다. 연구실에서는 trustworthy AI, healthcare analytics, user-centered evaluation methodologies 등 다양한 주제로 협업하고 있습니다.
Selected Sponsored Projects
-
Development of Worker-Friendly Innovative AI Agents for Autonomous Manufacturing (IITP, Apr 2025-Dec 2025)
Factory operations를 위한 multi-agent, multi-party engine과 retrieval-augmented orchestration pipeline을 구축했습니다. -
Data Construction and Optimization for Training/Inference of AI Chatbot (Samsung Fire & Marine Insurance, Mar 2025-Mar 2026)
Hierarchical documents를 활용한 document preprocessing architecture, PDF parsing modules, training dataset을 설계하고 구축하고 있습니다. -
Information Retrieval System for Scholarly Achievement and Research Projects (College of Engineering, SNU, Jan-Jul 2025)
Research metadata와 scientific content를 위한 evaluation protocols, metadata-driven corpora, dense retrievers를 개발했습니다. -
Large Language Model Evaluation Framework for the Financial Domain (KakaoBank, Nov 2023-Aug 2024)
Finance-domain LLM evaluation을 위해 safety, truthfulness, numerical reasoning benchmark와 evaluation pipeline을 구축했습니다. -
Developing Customer Content via Data Analysis Techniques (Stages 1 & 2) (LG Electronics, Apr 2022-Nov 2023)
Customer insight discovery를 위한 unsupervised dense retrieval, review clustering, anomaly detection, self-training pipeline을 개발했습니다.
협업이나 인턴십 관련 문의는 이메일로 연락 주세요.