About

Hi! I am Donghyun Kim, an AI researcher. I received my Ph.D. in Computer Science from Yonsei University, advised by Prof. Kyong-Ho Lee. During my Ph.D., I explored how to bridge the gap between knowledge graphs and real-world facts, with a focus on knowledge validation and refinement. Here is my CV.

My research focuses on Knowledge-Integrated AI, with the goal of building AI systems that can effectively acquire, organize, retrieve, and use knowledge. I am particularly interested in integrating structured and unstructured knowledge into AI systems in reliable and efficient ways. More recently, my research has expanded toward AI agents that can maintain and adapt evolving knowledge and memory over time, enabling reliable long-horizon reasoning and action.

Knowledge-Integrated AI
Knowledge Graphs · Large Language Models · Information Retrieval · Efficient Knowledge Integration
Trustworthy & Explainable AI
Knowledge Validation & Refinement · Evidence-Grounded Reasoning · Long-Horizon Agent Reliability

News

2026
Oct. NewI will be joining the Data Platform Research Group at AIST in Tokyo this December! 🗼
Aug. I received my Ph.D. in Computer Science from Yonsei University! 🎓
Aug. RADAR was accepted to IEEE Transactions on Knowledge and Data Engineering.
Jun. FineESC was accepted to IEEE Transactions on Affective Computing.
Apr. GraphRefine and CAPT were accepted to ACL 2026 (Main & Findings)! 🎉
Apr. I started as a Research Intern in the Agentic AI Lab at NC AI.

Education

  • Yonsei University Seoul, South Korea
    Ph.D. in Computer Science Sep. 2019 – Aug. 2026
  • Pusan National University Busan, South Korea
    B.S. in Computer Science and Engineering Mar. 2013 – Feb. 2017

Experience

  • NC AI Seongnam, South Korea
    Research Intern Apr. 2026 – Sep. 2026
  • Yonsei University Seoul, South Korea
    Graduate Researcher Sep. 2019 – Jun. 2026

Publications

CConference JJournal
  • 2026
  • J9
    Reliable Distillation of Recommendation Rationales from Large Language Models for Conversational Recommendation
    Hyeongjun Yang, Donghyun Kim, Kyuhwan Yeom, Kyong-Ho Lee, Byungkook Oh, and Xiongnan Jin
    IEEE Transactions on Knowledge and Data Engineering, 2026 (IF:11.6)
    Paper
  • J8
    FineESC: Fine-Grained Emotional Support Conversation with Turn-level Importance Modeling via Subquestion Reasoning
    Seokju Hwang, Midan Shim, Yeseul Gong, Donghyun Kim, and Kyong-Ho Lee
    IEEE Transactions on Affective Computing, 2026 (IF:11.3)
    Paper
  • C6
    LLMs as Knowledge Graph Refiners: Mitigating Factual Inconsistencies in Generative Knowledge Extraction
    Donghyun Kim, Hyeongjun Yang, Seokju Hwang, Kyong-Ho Lee, and Chanhee Lee
    ACL 2026 (Main, Acceptance Rate: 19%)
    Paper
  • C5
    Data-Efficient Adaptation to Contextual Shifts in LLM-based Conversational Recommendation
    Hyeongjun Yang, Donghyun Kim, Seokju Hwang, Midan Shim, Kyuhwan Yeom, Kaehyun Um, and Kyong-Ho Lee
    ACL 2026 (Findings)
    Paper
  • 2025
  • J7
    LLM-Assisted Ontology Restriction Verification with Clustering-based Description Generation
    Seungyeon Kim, Donghyun Kim, Seokju Hwang, Kyong-Ho Lee, and Kyunghwa Lee
    IEEE Access, 2025 (IF:4.2)
    Paper
  • J6
    Active Learning Framework for Improving Knowledge Graph Accuracy
    Donghyun Kim, Hyeongjun Yang, Seokju Hwang, Kyuhwan Yeom, Midan Shim, and Kyong-Ho Lee
    IEEE Access, 2025 (IF:4.2)
    Paper
  • J5
    CoreSense: Social Commonsense Knowledge-Aware Context Refinement for Conversational Recommender System
    Hyeongjun Yang, Donghyun Kim, Gayeon Park, Kyuhwan Yeom, and Kyong-Ho Lee
    IEEE Transactions on Knowledge and Data Engineering, 2025 (IF:11.6)
    Paper
  • J4
    Optimizing Training Data for Persona-Grounded Dialogue via Synthetic Label Augmentation
    Chanhee Lee, Donghyun Kim, Wongyu Kim, Kyungchan Lee, Youbin Ahn, Kyong-Ho Lee, Donghoon Shin, and Yeonsoo Lee
    Expert Systems With Applications, 2025 (IF:9.4)
    Paper
  • J3
    Multi-Domain Dialogue State Tracking via Dual Dynamic Graph with Hierarchical Slot Selector
    Yeseul Gong, Heeseon Kim, Seokju Hwang, Donghyun Kim, and Kyong-Ho Lee
    Knowledge-Based Systems, 2025 (IF:8.0)
    Paper
  • 2024
  • J2
    Dialogue Act-based Partner Persona Extraction for Consistent Personalized Response Generation
    Kyungchan Lee, Chanhee Lee, Donghyun Kim, and Kyong-Ho Lee
    Expert Systems With Applications, 2024 (IF:9.4)
    Paper
  • 2023
  • J1
    Active Learning for Cross-sentence N-ary Relation Extraction
    Seungmin Seo, Byungkook Oh, Jeongbeom Jeoung, Donghyun Kim, Kyong-Ho Lee, Donghoon Shin, and Yeonsoo Lee
    Information Sciences, 2023 (IF:6.0)
    Paper
  • C4
    Persona Expansion with Commonsense Knowledge for Diverse and Consistent Response Generation
    Donghyun Kim, Youbin Ahn, Wongyu Kim, Chanhee Lee, Kyungchan Lee, Kyong-Ho Lee, Jeonguk Kim, Donghoon Shin, and Yeonsoo Lee
    EACL 2023 (Main, Acceptance Rate: 24%)
    Paper
  • C3
    Concept-based Persona Expansion for Improving Diversity of Persona-Grounded Dialogue
    Donghyun Kim, Youbin Ahn, Chanhee Lee, Wongyu Kim, Kyong-Ho Lee, Donghoon Shin, and Yeonsoo Lee
    EACL 2023 (Main, Acceptance Rate: 24%)
    Paper
  • 2022
  • C2
    Emp-RFT: Empathetic Response Generation via Recognizing Feature Transitions between Utterances
    Wongyu Kim, Youbin Ahn, Donghyun Kim, and Kyong-Ho Lee
    NAACL 2022 (Main, Acceptance Rate: 21%)
    Paper
  • C1
    Active Learning on Pre-trained Language Model with Task-Independent Triplet Loss
    Seungmin Seo, Donghyun Kim, Youbin Ahn, and Kyong-Ho Lee
    AAAI 2022 (Main, Acceptance Rate: 15%)
    Paper