About Me

I am a PhD candidate in Computer Science at Hanyang University, advised by Taeuk Kim, and a researcher at the Hanyang University NLP Lab. I study dialogue systems and large language models with a focus on building conversational agents that stay robust in realistic settings where user behavior is complex, underspecified, and changes over time.

Research Interests

I focus on proactive conversational agents that reason beyond surface intent detection. My work models compound user intents, fluid shifts between task-oriented and open-domain dialogue, and latent preferences that emerge over long-term interaction context. I explore how LLM-based agents can abstract persistent preference patterns, manage dialogue flow proactively, and ground inferred preferences into structured decisions such as tool calls.

Keywords: Proactive conversational agents; Complex/compound intent understanding

Education

Ph.D. Candidate, Computer Science โ€” Hanyang University
Hanyang University NLP Lab. Advisor: Taeuk Kim.
M.S., Artificial Intelligence โ€” Hanyang University
Hanyang University NLP Lab. Thesis: Enhanced Multi-Intent Detection with Blended Datasets.
B.A. Economics & B.S. Statistics โ€” Sookmyung Womenโ€™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; โ€  Corresponding author.
Under Review
Latent Preference Reasoning for Multi-Session Personalized Tool-Calling
Yejin Yoon*, Minseo Kim*, Taeuk Kimโ€ .
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 Kimโ€ .
Paper ยท Code ยท Data
BlendX: Complex Multi-Intent Detection with Blended Patterns
Yejin Yoon, Jungyeon Lee, Kangsan Kim, Chanhee Park, Taeuk Kimโ€ .
Paper ยท Code ยท Data
Domestic Conferences
Show/Hide
Multi-Intent Detection for Korean Spoken Language
Yejin Yoon*, Jisoo Kim*, Jungmin Lim, Jungyeon Lee, Taeuk Kimโ€ .
Outstanding Paper Award.
Paper ยท Code ยท Data
A Multi-Intent Dataset Enhanced with Implicit Concatenation
Sungmin So*, Minji Woo*, Yejin Yoon, Jungyeon Lee, Taeuk Kimโ€ .
Paper
Enhanced Prompting for Multi-Label Classification
Jungyeon Lee, Youngwoo Shin, Yejin Yoon, Taeuk Kimโ€ .
Paper
KoLegal-BERT: Legal Language Representation Model for Legal Domain Text Mining
Sangmin Park*, Yejin Yoon*, Jaeyoun Lee, Jaieun Kimโ€ .
Paper

Patent

International Patents
METHOD AND APPARATUS FOR GENERATING MULTI-INTENT UTTERANCE DATASETS
็”จไบŽ็”Ÿๆˆๅคšๆ„ๅ›พ่ฏ่ฏญๆ•ฐๆฎ้›†็š„ๆ–นๆณ•ๅ’Œ่ฃ…็ฝฎ
Domestic Patents
Show/Hide
์„ ํ˜ธ ๊ธฐ๋ฐ˜ ์ „ํ™˜ ์ธ์ง€ํ˜• ๋Œ€ํ™”๋ชจ๋ธ์˜ ํ•™์Šต์„ ์œ„ํ•œ ๋ฐฉ๋ฒ• ๋ฐ ์žฅ์น˜
์ „ํ™˜ ์ธ์ง€ํ˜• ๋Œ€ํ™” ๋ฐ์ดํ„ฐ์…‹์˜ ์ƒ์„ฑ ๋ฐ ๊ฒ€์ฆ์„ ์œ„ํ•œ ๋ฐฉ๋ฒ• ๋ฐ ์žฅ์น˜
๋‹จ์ผ ์˜๋„ ๋ฐœํ™”๋ฅผ ๋‹ค์ค‘ ์˜๋„ ๋ฐœํ™”๋กœ ํ™•์žฅํ•˜๊ธฐ ์œ„ํ•œ ๊ทœ์น™ ํ™œ์šฉ ๋ฐฉ์‹๊ณผ ์ƒ์„ฑํ˜• ์ธ๊ณต์ง€๋Šฅ ๋ชจ๋ธ ํ™œ์šฉ์„ ๊ฒฐํ•ฉํ•œ ๋ฐœํ™” ๋ณ‘ํ•ฉ ๊ธฐ์ˆ 
๋‹ค์ค‘ ํŽ˜๋ฅด์†Œ๋‚˜๋ฅผ ์ด์šฉํ•œ ๋Œ€ํ™” ๋ฐฉ๋ฒ•, ๋‹ค์ค‘ ํŽ˜๋ฅด์†Œ๋‚˜๋ฅผ ์ด์šฉํ•œ ๋Œ€ํ™” ์žฅ์น˜ ๋ฐ ํŽ˜๋ฅด์†Œ๋‚˜ ๋ถ„๋ฅ˜๋ชจ๋ธ์˜ ํŠธ๋ ˆ์ด๋‹ ๋ฐฉ๋ฒ•

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 ์ดˆ์žฅ๊ธฐ๊ธฐ์–ต ๊ธฐ๋ฐ˜ ๋Œ€ํ™”ํ˜• ์—์ด์ „ํŠธ
Multi-Intent Modeling for Advanced Speech Recognition ์Œ์„ฑ์ธ์‹ ๊ณ ๋„ํ™”๋ฅผ ์œ„ํ•œ ๋ณตํ•ฉ์˜๋„ ๋ชจ๋ธ ์—ฐ๊ตฌ
Natural Language-Based Compound Intent Algorithms ์ž์—ฐ์–ด ๊ธฐ๋ฐ˜ ๋ณตํ•ฉ ์˜๋„ ์•Œ๊ณ ๋ฆฌ์ฆ˜ ์—ฐ๊ตฌ

Teaching

Teaching Assistant
Natural Language Processing
Guest Speaker
CS Graduate Program Info Session
Topic: Graduate school life and research advice
Graduate School of Artificial Intelligence Convergence Info Session
Topic: Industry-academia projects, dialogue systems
Natural Language Processing
Topic: Recent task-oriented dialogue (TOD) system research
Student Mentoring
CAPSTONE SOFTWARE PROJECT 2
CAPSTONE SOFTWARE PROJECT 1

Academic Services

Reviewer

Talks

Invited Talks
Practical Strategies for Overcoming the Limits of LLM Dialogue Capacity LLM์˜ Dialogue Capacity ํ•œ๊ณ„๋ฅผ ๊ทน๋ณตํ•˜๊ธฐ ์œ„ํ•œ ์‹ค๋ฌด์ ์ธ ๋Œ€์‘ ์—ฐ๊ตฌ
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

Contact

Open to exploratory research discussions and potential collaborations related to dialogue systems, conversational AI, and NLP.
Also available for invited academic talks and guest lectures.
* Email: stillwithyou [at] hanyang.ac.kr