About Me
I am a PhD candidate in Computer Science at Hanyang University, advised by Prof. Taeuk Kim. My research focuses on conversational AI and large language model-based dialogue systems, with the goal of enabling conversational agents to support natural and adaptive interactions with users.
My work explores how dialogue systems can move beyond single-turn task completion toward long-horizon interactions that reflect evolving user intents, preferences, and conversational context. To study this problem, I design dialogue models, construct large-scale datasets, and develop evaluation frameworks for complex conversational behaviors.
More recently, I have been investigating memory-augmented and preference-aligned conversational agents, focusing on how systems can accumulate knowledge about users across multiple sessions and adapt their responses accordingly. My broader goal is to build conversational AI systems that support context-aware, personalized, and long-term human-AI interaction.
Research Interests
My research focuses on conversational AI and large language model–based dialogue systems, particularly on enabling agents to maintain adaptive, long-term interactions with users.
My main research interests include:
Personalized Conversational Agents
- Modeling user preferences and behavioral patterns across interactions
- Memory-augmented dialogue systems for long-term personalization
Long-Horizon Dialogue Modeling
- Multi-intent and transition-aware dialogue understanding
- Integrating task-oriented dialogue and open-domain conversation
LLM-based Interactive Systems
- Tool-using conversational agents and structured action generation
- Scalable datasets and evaluation frameworks for conversational AI
Education
Ph.D. Candidate, Computer Science — Hanyang University
Hanyang University NLP Lab. Advisor: Taeuk Kim.
M.S., Artificial Intelligence — Hanyang University
Hanyang University NLP Lab. Advisor: Taeuk Kim.
(Thesis: Enhanced Multi-Intent Detection with Blended Datasets.)
(Thesis: Enhanced Multi-Intent Detection with Blended Datasets.)
B.A. Economics & B.S. Statistics — Sookmyung Women’s University
Experience
Researcher, KT (Internship)
KT AI2XL Research Lab. Large AI application P-TF emotional dialogue system project.
Researcher, Saltlux (Full-time)
AI Labs advanced research team.
Publications
* Equal Contribution; † Corresponding author.
Under Review
Latent Preference Reasoning for Multi-Session Personalized Tool-Calling
Yejin Yoon*, Minseo Kim*, Taeuk Kim†.
International Conferences
Beyond Task-Oriented and Chitchat Dialogues: Proactive and Transition-Aware Conversational Agents
Yejin Yoon, Yuri Son, Namyoung So, Minseo Kim, Minsoo Cho, Chanhee Park, Seungshin Lee, Taeuk Kim†.
Project Page · Paper · Code · Data
Project Page · Paper · Code · Data
BlendX: Complex Multi-Intent Detection with Blended Patterns
Domestic Conferences
Show/Hide
Multi-Intent Detection for Korean Spoken Language
A Multi-Intent Dataset Enhanced with Implicit Concatenation
Sungmin So*, Jiwoo Min*, Yejin Yoon, Jungyeon Lee, Taeuk Kim†.
Paper
Paper
Enhanced Prompting for Multi-Label Classification
Jungyeon Lee, Youngwoo Shin, Yejin Yoon, Taeuk Kim†.
Paper
Paper
KoLegal-BERT: Legal Language Representation Model for Legal Domain Text Mining
Sangmin Park*, Yejin Yoon*, Jaeyoun Lee, Jaieun Kim†.
Paper
Paper
Patents
International Patents
METHOD AND APPARATUS FOR GENERATING MULTI-INTENT UTTERANCE DATASETS
用于生成多意图话语数据集的方法和装置
Domestic Patents
Show/Hide
선호 기반 전환 인지형 대화모델의 학습을 위한 방법 및 장치
전환 인지형 대화 데이터셋의 생성 및 검증을 위한 방법 및 장치
단일 의도 발화를 다중 의도 발화로 확장하기 위한 규칙 활용 방식과 생성형 인공지능 모델 활용을 결합한 발화 병합 기술
다중 페르소나를 이용한 대화 방법, 다중 페르소나를 이용한 대화 장치 및 페르소나 분류모델의 트레이닝 방법
Awards and Honors
Seoul Tech Scholarship
Excellence Scholarship for Doctoral Students
KCC 2024 Outstanding Paper Award
Multi-Intent Detection for Korean Spoken Language
Outstanding Achievement Award (Graduation Excellence)
Projects
Conversational Agents with Hyper Long-Term Memory 초장기기억 기반 대화형 에이전트
- Led research on hyper long-term memory for conversational agents, focusing on persistent preference tracking and multi-session personalization.
- Designed a preference-aware memory framework that links long-horizon user behavior to structured tool-calling decisions.
- Built end-to-end pipelines for long-context data construction, memory-grounded modeling, and evaluation under realistic multi-session settings.
- Developing robust methods for preference abstraction and retrieval to improve consistency, controllability, and practical deployment of proactive dialogue agents.
Multi-Intent Modeling for Advanced Speech Recognition 음성인식 고도화를 위한 복합의도 모델 연구
- Led foundational research on transition-aware multi-intent conversational AI, resulting in an EMNLP 2025 main conference publication.
- Designed and developed a preference-aligned dialogue framework integrating dataset construction, hybrid LLM-based validation, and multi-intent reasoning.
- Owned the end-to-end research and development pipeline, from modeling and data infrastructure to deployment of an LLM-based input analysis module for in-vehicle voice assistants.
- Directed project execution in an industry-academia collaboration, coordinating research contributors, managing milestones, and delivering deployable system outcomes.
Natural Language-Based Compound Intent Algorithms 자연어 기반 복합 의도 알고리즘 연구
- Led research on multi-intent understanding for speech-based dialogue systems, addressing limitations of single-intent voice interaction models.
- Initiated and directed the construction of a large-scale multi-intent conversational dataset designed to model complex and transition-aware user interactions.
- Designed and led the development of a speech utterance segmentation-based multi-intent detection algorithm enabling accurate identification of multiple intents within a single user query.
- Resulted in a long paper publication at LREC-COLING 2024 and domestic and international patent applications derived from the proposed dataset construction and modeling methodology.
- Oversaw end-to-end research execution, organizing datasets, algorithms, and experimental frameworks into reproducible research artifacts.
Teaching
Teaching Assistant
Natural Language Processing
Guest Speaker
Computer Science Graduate Admissions Information Session
Topic: Graduate school life and research advice
Graduate School of Applied Artificial Intelligence Information Session
Topic: Industry-academia projects, dialogue systems
Natural Language Processing (Guest Lecturer)
Topic: Recent task-oriented dialogue (TOD) system research
Student Mentoring
CAPSTONE SOFTWARE PROJECT 2
CAPSTONE SOFTWARE PROJECT 1
Academic Services
AI Ambassador, Kakao (KANANA 429, AI Expert Track)
Kakao AI.
Reviewer
Talks
Invited Talks
Practical Strategies for Overcoming the Limits of LLM Dialogue Capacity LLM의 Dialogue Capacity 한계를 극복하기 위한 실무적인 대응 연구
Topic: Recent chatbot and dialogue system using large language models
Contributed Talks
BlendX: Complex Multi-Intent Detection with Blended Patterns
Topic: Recent task-oriented dialogue (TOD) system research
Recent Presentations
Recent Posts
Contact
I’m always open to research conversations, collaborations, and invited talks/guest lectures.
If you’d like to get in touch, please email me at stillwithyou [at] hanyang.ac.kr.
Please note that response times may vary depending on current commitments.
If you’d like to get in touch, please email me at stillwithyou [at] hanyang.ac.kr.
Please note that response times may vary depending on current commitments.