About
Hi! I am Donghyun Kim, an AI researcher open to postdoctoral and research scientist opportunities. 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 Agentic AI, with the goal of building AI systems that can effectively acquire, organize, retrieve, and use knowledge. I am particularly interested in how structured and unstructured knowledge can be integrated into AI systems in an efficient and reliable manner. More recently, my research has expanded toward AI agents that can maintain and adapt evolving knowledge and memory over time, ultimately enabling reliable long-horizon reasoning and action.
Knowledge-Integrated AI
Knowledge Graphs · AI Agents · Information Retrieval · Efficient Knowledge Integration
Trustworthy & Explainable AI
Knowledge Validation & Refinement · Evidence-Grounded Reasoning · Long-Horizon Agent Reliability
News
2026
Aug.
NewI received my Ph.D. in Computer Science from Yonsei University🎓
Aug.
NewRADAR 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 at NC AI.
Education
-
Yonsei University Seoul, South KoreaPh.D. in Computer Science Sep. 2019 – Aug. 2026
-
Pusan National University Busan, South KoreaB.S. in Computer Science and Engineering Mar. 2013 – Feb. 2017
Experience
-
NC AI Seongnam, South KoreaResearch Intern Apr. 2026 – Present
-
Yonsei University Seoul, South KoreaGraduate Researcher Sep. 2019 – Jun. 2026
Publications
International Conferences
-
C6 LLMs as Knowledge Graph Refiners: Mitigating Factual Inconsistencies in Generative Knowledge ExtractionACL 2026 (Main, Acceptance Rate: 19%)
-
C5 Data-Efficient Adaptation to Contextual Shifts in LLM-based Conversational RecommendationACL 2026 (Findings)
-
C4 Persona Expansion with Commonsense Knowledge for Diverse and Consistent Response GenerationEACL 2023 (Main, Acceptance Rate: 24%)
-
C3 Concept-based Persona Expansion for Improving Diversity of Persona-Grounded DialogueEACL 2023 (Main, Acceptance Rate: 24%)
-
C2 Emp-RFT: Empathetic Response Generation via Recognizing Feature Transitions between UtterancesNAACL 2022 (Main, Acceptance Rate: 21%)
-
C1 Active Learning on Pre-trained Language Model with Task-Independent Triplet LossAAAI 2022 (Main, Acceptance Rate: 15%)
International Journals
-
J9 Reliable Distillation of Recommendation Rationales from Large Language Models for Conversational RecommendationIEEE Transactions on Knowledge and Data Engineering, 2026 (IF:11.6)
-
J8 FineESC: Fine-Grained Emotional Support Conversation with Turn-level Importance Modeling via Subquestion ReasoningIEEE Transactions on Affective Computing, 2026 (IF:11.3)
-
J7 LLM-Assisted Ontology Restriction Verification with Clustering-based Description GenerationIEEE Access, 2025 (IF:4.2)
-
J6 Active Learning Framework for Improving Knowledge Graph AccuracyIEEE Access, 2025 (IF:4.2)
-
J5 CoreSense: Social Commonsense Knowledge-Aware Context Refinement for Conversational Recommender SystemIEEE Transactions on Knowledge and Data Engineering, 2025 (IF:11.6)
-
J4 Optimizing Training Data for Persona-Grounded Dialogue via Synthetic Label AugmentationExpert Systems With Applications, 2025 (IF:9.4)
-
J3 Multi-Domain Dialogue State Tracking via Dual Dynamic Graph with Hierarchical Slot SelectorKnowledge-Based Systems, 2025 (IF:8.0)
-
J2 Dialogue Act-based Partner Persona Extraction for Consistent Personalized Response GenerationExpert Systems With Applications, 2024 (IF:9.4)
-
J1 Active Learning for Cross-sentence N-ary Relation ExtractionInformation Sciences, 2023 (IF:6.0)
Patents
-
P7 Method for Refining Knowledge Graph and System thereforKR Patent, filed Jun. 8, 2026 (No. 10-2026-0103475)
-
P6 Ontology Restriction Verification System and the Method thereofKR Patent, filed Nov. 14, 2025 (No. 10-2025-0172318)
-
P5 Method and Apparatus for Retrieval-Augmented Knowledge Graph Validation using Large Language ModelKR Patent, filed Jul. 7, 2025 (No. 10-2025-0090580)
-
P4 Active Learning Method and Apparatus for Improving Knowledge Graph AccuracyKR Patent, filed Oct. 29, 2024 (No. 10-2024-0149277)
-
P3 Fact Verification Method based on Domain Ontology and Apparatus thereofKR Patent, filed Oct. 29, 2024 (No. 10-2024-0149276); granted May 11, 2026 (No. 10-2964955)
-
P2 Method and Apparatus for Generating Empathetic Responses via Recognizing Emotion and Keyword Transitions between UtterancesKR Patent, filed Mar. 15, 2023 (No. 10-2023-0034098); granted Aug. 20, 2026 (No. 10-3008991)
-
P1 Method and Apparatus for Generating Extended Persona SentencesKR Patent, filed Dec. 31, 2021 (No. 10-2021-0194377); granted Sep. 11, 2025 (No. 10-2860494)