Faculty

Seonghyeon Lee

Assistant Professor

School of Computer Science and Engineering, Kyungpook National University, Daegu, South Korea

Language Modeling, Code Language Models, Evaluation, Coding Agent

sh0416{at}knu.ac.kr

CV

Google ScholarDBLPSemantic ScholarACL AnthologyOpenReviewORCIDGitHubLinkedIn

Biography

I am an assistant professor at the School of Computer Science and Engineering, Kyungpook National University (KNU), and a faculty member of the Data & Language Intelligence Lab. My research focuses on language models for code: how they reason over code, use tools and repository-level context, and work as reliable coding agents, along with how to evaluate them.

I received my Ph.D. in Computer Science and Engineering from POSTECH, advised by Prof. Hwanjo Yu. Before joining KNU, I was a postdoctoral researcher at the POSTECH Data Intelligence Lab and a machine learning researcher at ScatterLab.

Education

• Mar. 2018 – Aug. 2024 Ph.D. in Computer Science and EngineeringPOSTECH · Thesis: Leveraging Relational Knowledge with Pretrained Language Models · Advisor: Prof. Hwanjo Yu
• Mar. 2014 – Feb. 2018 B.S. in Computer Science and Engineering, Summa Cum LaudePOSTECH

Experience

• Mar. 2025 – Present Assistant ProfessorSchool of Computer Science and Engineering, Kyungpook National University
• Sep. 2024 – Feb. 2025 Postdoctoral ResearcherData Intelligence Lab, Department of Computer Science and Engineering, POSTECH
• Feb. 2023 – Feb. 2024 Machine Learning ResearcherScatterLab
• Feb. 2021 – Feb. 2023 Visiting ResearcherScatterLab
• Jul. – Aug. 2017 InternNAVER
• Jul. – Aug. 2016 InternKakao

Honors & Awards

• Sep. 2022 NAVER Ph.D. Fellowship
• Jun. 2022 Best Poster Award (3rd)POSTECH–NAVER AI Day
• Jun. 2017 3rd PrizePOSTECH Programming Contest (PPC)
• Jun. 2015 Rookie AwardPOSTECH Programming Contest (PPC)

Invited Talks

• May 14, 2025 Generative Code Language ModelsSeminar, Pukyong National University
• Jun. 17, 2024 Evaluating Generative Language ModelsEECS Seminar, DGIST

Teaching

• Fall 2026 Natural Language Processing자연언어처리COME0746Graduate
• Fall 2026 Introduction to Reinforcement Learning강화학습개론CAIB0216Undergraduate
• Spring 2026 Reinforcement Learning강화학습ARIN0710Graduate
• Spring 2026 Fundamentals of Data Science데이터과학기초ITEC0419Undergraduate
• Fall 2025 Introduction to Natural Language Processing자연어처리개론CAIB0211Undergraduate
• Fall 2025 Introduction to Reinforcement Learning강화학습개론CAIB0216Undergraduate
• Spring 2025 AI Convergence Applications인공지능융합응용GRAD0732Graduate
• Spring 2025 Open Source Programming오픈소스프로그래밍GLSO0215Undergraduate

Professional Service

• Oct. 2026 Senior Program Committee MemberAAAI-27
• Nov. 2025 ReviewerACM Transactions on Software Engineering and Methodology (TOSEM)
• Oct. 2025 Area ChairACL Rolling Review (October 2025 cycle)
• Aug. 2025 Program Committee MemberAAAI-26
• Sep. 2023 – Present ReviewerACL Rolling Review
• Apr. 2024 ReviewerKorea Software Congress (KSC)
• Sep. – Oct. 2023 ReviewerArtificial Intelligence Review

Publications 18

2026

• IEICE Trans. Inf. & Syst.

  Accelerating Sequential Pattern Mining on Spark: A SPADE-Based Approach

  Yeonsu Park, Seonghyeon Lee

  IEICE Transactions on Information and Systems, 2026, Vol. E109.D, No. 2, pp. 273–278 (SCI-E)

  Paper

• IEEE Access

  Minimizing Response Latency in LLM-Based Agent Systems: A Comprehensive Survey

  Gyeongmuk Park, Seonghyeon Lee, Yeonsu Park

  IEEE Access, 2026, Vol. 14, pp. 26140–26168 (SCI-E)

  Paper

• IEICE Trans. Inf. & Syst.

  Augmented Code Language Models: A Survey on Advanced Code Intelligence

  Seonghyeon Lee, Gyeongmuk Park, Jeongmin Kim, Yeonsu Park

  IEICE Transactions on Information and Systems, 2026

  Paper

• ICMR 2026

  On the Effectiveness of Integration Methods for Multimodal Dialogue Response Retrieval

  Seongbo Jang, Seonghyeon Lee, Dongha Lee, Hwanjo Yu

  The 16th ACM International Conference on Multimedia Retrieval

  Paper

• EMNLP 2026 Main

  Layer-wise Target Propagation: Efficient Component Attribution through Target Centric Propagation

  Lasse Marten Jantsch, Dong-Jae Koh, Seonghyeon Lee*, Young-Kyoon Suh* (*: Corresponding authors)

  Acceptance rate: 15.4%

  arXiv

2025

• ACL 2025 Findings

  Verbosity-Aware Rationale Reduction: Sentence-Level Rationale Reduction for Efficient and Effective Reasoning

  Joonwon Jang, Jaehee Kim, Wongin Kweon, Seonghyeon Lee, Hwanjo Yu

  Findings of the Association for Computational Linguistics: ACL 2025

  Paper

• EMNLP 2025 Findings

  How Diversely Can Language Models Solve Problems? Exploring the Algorithmic Diversity of Model-Generated Code

  Seonghyeon Lee, HeeJae Chon, Joonwon Jang, Dongha Lee, Hwanjo Yu

  Findings of the Association for Computational Linguistics: EMNLP 2025

  Paper arXiv

2024

• LREC-COLING 2024

  KoDialogBench: Evaluating Conversational Understanding of Language Models with Korean Dialogue Benchmark

  Seonghyeon Lee*, Seongbo Jang*, Hwanjo Yu (*: Equal contribution)

  Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation

  Paper arXiv

• NAACL 2024 Findings

  Exploring Language Model’s Code Generation Ability with Auxiliary Functions

  Seonghyeon Lee, Sanghwan Jang, Seongbo Jang, Dongha Lee, Hwanjo Yu

  Findings of the Association for Computational Linguistics: NAACL 2024

  Paper arXiv

• EMNLP 2024 Findings

  Eliciting Instruction-tuned Code Language Models’ Capabilities to Utilize Auxiliary Function for Code Generation

  Seonghyeon Lee, Suyeon Kim, Joonwon Jang, HeeJae Chon, Dongha Lee, Hwanjo Yu

  Findings of the Association for Computational Linguistics: EMNLP 2024

  Paper

2023

• AAAI 2023

  Learning Topology-Specific Experts for Molecular Property Prediction

  Suyeon Kim, Dongha Lee, Seongku Kang, Seonghyeon Lee, Hwanjo Yu

  Proceedings of the 37th AAAI Conference on Artificial Intelligence

  Paper arXiv

2022

• ACL 2022

  Toward Interpretable Semantic Textual Similarity via Optimal Transport-based Contrastive Sentence Learning

  Seonghyeon Lee, Dongha Lee, Seongbo Jang, Hwanjo Yu

  Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

  Paper arXiv

• EMNLP 2022 Findings

  Topic Taxonomy Expansion via Hierarchy-Aware Topic Phrase Generation

  Dongha Lee, Jiaming Shen, Seonghyeon Lee, Susik Yoon, Hwanjo Yu, Jiawei Han

  Findings of the Association for Computational Linguistics: EMNLP 2022

  Paper arXiv

2021

• ACL 2021

  OoMMix: Out-of-manifold Regularization in Contextual Embedding Space for Text Classification

  Seonghyeon Lee, Dongha Lee, Hwanjo Yu

  Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

  Paper arXiv

• AAAI 2021

  Learnable Dynamic Temporal Pooling for Time Series Classification

  Dongha Lee, Seonghyeon Lee, Hwanjo Yu

  Proceedings of the 35th AAAI Conference on Artificial Intelligence

  Paper arXiv

• ICDM 2021

  Learnable Structural Semantic Readout for Graph Classification

  Dongha Lee, Suyeon Kim, Seonghyeon Lee, Chanyoung Park, Hwanjo Yu

  2021 IEEE International Conference on Data Mining

  Paper arXiv

2019

• KCC 2019

  Attention Mechanism for Sequential Recommendation

  Seonghyeon Lee, Hwanjo Yu

  Korea Computer Congress 2019

• CIKM 2019

  BHIN2vec: Balancing the Type of Relation in Heterogeneous Information Network

  Seonghyeon Lee, Chanyoung Park, Hwanjo Yu

  Proceedings of the 28th ACM International Conference on Information and Knowledge Management

  Paper arXiv