Current Positions
- Principal Researcher at Human-Inspired AI Research (Korea University)
- Registered Director at Next Generation Artificial Intelligence Convergence Association
Specialization
Research Interests
Education
MS Computer Science (4.44/4.50) 2008-2020
Korea University, Seoul, Korea
Thesis: The Method for Predicting Real Estate Price Using Recurrent Neural Network / Advisor: Prof. Soonyoung Jung
BS Computer Science Engineer (3.46/4.50) 2004-2008
Korea University, Seoul, Korea
Awards
Selected for the 2025 Top 100 National R&D Achievements 2025
Recognized for contributions through research on truthfulness and consistency in generative AI outputs. Served as PM for KULLM (2023) and KURE (2024), overseeing the entire lifecycle from model development to deployment.
Best Paper Award 2015
"Design and Implementation of Simulator for educating Parallel K-Means", Korean Association of Computer Education Conference
3rd Place, Plagiarism Detection Competition 2013
"CopyCaptor: Plagiarized Source Retrieval System using Global word frequency and Local feedback", PAN at CLEF 2013
Experience
Co-authored Textbook 2025
Korea National Open University Press
"Open Source-based Data Analysis"
Teaching Assistant 2022~
Korea University
AI Practice
Part-time Lecturer 2019~
Korea National Open University
Cloud System, Database
Teaching Assistant 2019~
Korea National Open University (PRIME COLLEGE)
Python
Military Service Exempted Technical Research Personnel 2011-2014
Korea University, Seoul, Korea
Open Source Contributions
Selected Projects
2025~
Development of Startup Customized Growth Support Platform Based on Ultra-large AI Core Technology
KIAT, HIAI Research
2024~
Research on Ensuring Truthfulness and Consistency of Generative AI Outputs
NRF, HIAI Research
2024
GLiNER-ko
HIAI Research
2024
Ko-Gemma
HIAI Research
2024
Vector Embedding Construction and Similarity Search Technology Development
OnTheIT, HIAI Research
2023
Gaon-Large Language Model
Gaon Platform, HIAI Research
2023
AI-based Ore Deposit Prediction Model
KIGAM, HIAI Research
2023-2025
Construction Standard Digital Transformation: Library and Ontology Development
KICT, HIAI Research
2023
KULLM
HIAI Research
2021~
Human Inspired AI Research
NRF, HIAI Research
2022-2023
Development of Interactive Book Recommendation Device Through AI-based Voice Analysis
IITP, CHAEUM CNI, HIAI Research
2022-2023
Construction Standard Digitalization Data Standardization Research
KICT, HIAI Research
2021-2022
Development of AI Customer Center using MRC-based Automatic QA System
IITP, O2O, HIAI Research
2021-2022
AI-based Real-time Online Marketing Performance Prediction System
IITP, BizSpring, HIAI Research
2021
EBS AI Learning Diagnosis System Model Validation and Improvement
EBS, HIAI Research
2020-2022
AI Structured Interview and Scoring System Reflecting Face-to-face Interview Characteristics
IITP, Withmind, HIAI Research
2019-2020
REPAN, Real Estate Price Prediction
REPAN, WITHCAT
2016-2020
Genetree Realtime PCR Viewer
Genetree, WITHCAT
2012-2020
Biosewoom Realtime PCR Viewer
Biosewoom, KnP Solution, WITHCAT
2015-2020
Development of Chemical Accident Behavior Analysis/Damage Prediction Models and Environmental Risk Map Technology
KEITI, Korea University
2018-2019
Educhain: Blockchain-based Decentralized Online Judge Coding DAPP Research
NRF, Korea University
2018
Roboreport
Samsung Startup Incubating Program, Connectdot
2016-2018
Multidimensional Semantics-based Predictive Mobility Aggregation Analysis
NRF, Korea University
2016-2018
Research on Personalized Coding Learning System Using Lexical-Syntactic-Semantic Feature Extraction
NRF, Korea University
2017
Language Rehabilitation Training
MOHW, MAAUM
2016-2017
Unitek Lion6
Unitek, KnP Solution
2015
Language Rehabilitation Program
MOHW, Korea University
2013-2015
Cluster-based Distributed Management and Query Processing of Ultra-large Moving Trajectory Data for Next-gen LBS
NRF, Korea University
2012-2013
Structural Analysis and Collaborative R&D Framework for Converged Contents
NRF, Korea University
2011-2013
3D Spatial Query Technology for Real-time Location-based Mobile Augmented Reality Services
NRF, Korea University
2008-2012
Environmental Toxicity and Endocrine/Neurodegenerative Disease DB Construction
NRF, Korea University
Publications
2025
MMTEB: Massive Multilingual Text Embedding Benchmark
ICLR 2025 Conference
2025
Evaluation of Topic Models with regard to N-gram Changes in Topic Representations: Focusing on Coherence and Diversity
Journal of Internet Computing and Services 26.1 (2025): 19-33
2024
Intelligent Predictive Maintenance RAG framework for Power Plants: Enhancing QA with StyleDFS and Domain Specific Instruction Tuning
EMNLP 2024 (Industry Track)
2024
KoE5: A New Dataset and Model for Improving Korean Embedding Performance
HCL Technology 36th Annual Conference, pp. 239-244
2024
Building Korean Embedding Benchmarks with Large Language Models
HCL Technology 36th Annual Conference, pp. 182-186
2024
X-Optimization for Language Transfer
HCL Technology 36th Annual Conference, pp. 89-93
2024
Topic Analysis of Population Aging using NLP Technology
Journal of Korean IT Service Society, 23(1), 55-79
2023
Assessing the Retrieval-based Generation Capabilities of Large Language Models: A Call for a New Benchmark
ICICPE 2023, 9-11
2023
Evaluating ChatGPT Proficiency in Table QA: Exploring Generative Models in Structured Data Understanding
ICICPE 2023
2023
KULLM: Learning to Construct Korean Instruction-following Large Language Models
Annual Conference on Human and Language Technology, 196-202
2023
KFREB: Korean Fictional Retrieval-based Evaluation Benchmark for Generative Large Language Models
Annual Conference on Human and Language Technology, 9-13
2023
QA Pair Passage RAG-based LLM Korean chatbot service
Annual Conference on Human and Language Technology, 683-689
2023
Comparative analysis of large language model Korean quality based on zero-shot learning
Annual Conference on Human and Language Technology, 722-725
2022
Return on Advertising Spend Prediction with Task Decomposition-Based LSTM Model
Mathematics, 1637
2022
Dense-to-Question and Sparse-to-Answer: Hybrid Retriever System for Industrial Frequently Asked Questions
Mathematics, 1335
2021
Semantic Similarity Retriever for Industrial Question Answering System
IRCPE 2021
2021
Prediction of Return on Advertising Spend Leveraging Keyword Information
IRCPE 2021
2020
Korean Q&A Chatbot for COVID-19 News Domains Using Machine Reading Comprehension
Annual Conference on Human and Language Technology, 540-542
2018
Information retrieval service for chemical accident response using messenger Chat bot
Proceedings of Korea Information Processing Society Conference, 467-469
2018
The Retrieval of Regions with Similar Tendency in Geo-Tagged Dataset
CUTE 2019/CSA 2018 LNEE 536, 42-47
2018
Spatial Clustering based Meteorological Fields Construction for Regional Vulnerability Assessment
INSIGHT-Indonesian Society for Knowledge and Human Development
2018
Plagiarism Detection on Source Code using Deep Learning Sentence Embedding
IRCPE 2018
2018
PyTicker: Relative Normalized Price Ratio Monitor between Cryptocurrency Exchanges
IRCPE 2018
2017
Deep Representation of Raw Traffic Data: An Embed-and-Aggregate Framework for High-Level Traffic Analysis
CUTE 2017, CSA 2017
2017
A corpus-based approach to classifying emotions using Korean linguistic features
Cluster Computing, 583-595
2016
Improvement of position accuracy of geocoded coordination based on Ensemble method
Proceedings of Korea Information Processing Society Conference, 818-819
2015
Online coding skill learning system for Teaching and learning C language
Proceedings of Korea Information Processing Society Conference, 1659-1661
2015
Design and Implementation of Simulator for educating Parallel K-Means
Korean Association of Computer Education Conference, 101-105
2015
Design and Implementation of DBSCAN Learning Simulator
Korean Association of Computer Education Conference, Vol.19 No.1
2014
Identifying non-elliptical entity mentions in a coordinated NP with ellipses
Journal of Biomedical Informatics, 139-152
2013
CopyCaptor: Plagiarized source retrieval system using global word frequency and local feedback
Working Notes for CLEF Conference
2013
An unordered n-gram model for Plagiarism Detection
International Conference on Convergence Technology
2012
A Study on the Key Competency of Converged Contents: Focused on the ICT and Eco-system Viewpoints
Proceedings of Korea Information Processing Society Conference, 1281-1283
2012
Automatic extraction of user's search intention from web search logs
Multimedia Tools and Applications
2012
Integrated Environmental Toxicology and Genomic Information System
Korean Association of Computer Education Conference, 255-258
2011
The partial matching method for effective recognizing HLA entities
The Journal of Korean Association of Computer Education, 83-94
2010
Extracting Search Intentions from Web Search Logs
ICISS 2010
2010
Development of the QSTR model generation software using machine learning methods
ICONIC 2010
2009
Automatic Extract User Intention from Web Search Log
2010 2nd International Conference on ITCS, 21-32
2009
Automatic extraction of HLA-disease interaction information from biomedical literature
Advances in Computational Science and Engineering (SCOPUS), pp. 219-230