Nakyeong Yang (양낙영)
Postdoctoral Researcher
Max Planck Institute for Software Systems
About
I am a postdoctoral researcher in Artificial Intelligence at Max Planck Institute for Software Systems. My research focuses on Large Language Models (LLMs) and Interpretable & Safe AI. I investigate how knowledge is represented at the neuronal level in LLMs and how it manifests in model behavior.
News
- [2026.08] One paper (Personalization) is accepted to EMNLP 2026. NEW
- [2026.06] I joined Max Planck Institute for Software Systems as a Postdoctoral Researcher. NEW
- [2026.06] Two papers (Agent, Personalization) are accepted to ICML 2026 Workshops.
- [2026.04] Three papers (Pretraining, Unlearning, Self-consistency) are accepted to ACL 2026.
- [2025.08] Two papers (Unlearning, Pretraining) are accepted to ICLR 2026.
- [2026.01] One paper (Persona) is accepted to EACL 2026.
- [2025.12] I defended my Ph.D!
- [2025.11] One paper (Math reasoning) is accepted to AAAI 2026.
- [2025.10] One paper (Persona) is accepted to IJCNLP-AACL 2025.
- [2025.08] Two papers (Unlearning, Story generation) are accepted to EMNLP 2025.
- [2025.08] One paper (Compression) is accepted to CIKM 2025.
- [2024.08] I joined Max Planck Institute for Security and Privacy as a research intern.
- [2024.07] One paper (Video moment retrieval) is accepted to CIKM 2024.
- [2024.05] One paper (AI Safety) is accepted to ACL 2024.
- [2023.09] I joined LG AI Research as a research intern.
Publication
2026
EMNLP 2026 Findings (& ICML 2026 FoGen)
ICML 2026 AIWILD
ACL 2026 Findings
[18]
How Training Data Shapes the Use of Parametric and In-Context Knowledge in Language Models
PDF
Code
ACL 2026
ACL 2026 Findings
ICLR 2026
ICLR 2026
AAAI 2026
2025
[12]
Persona is a Double-edged Sword: Rethinking the Impact of Role-play Prompts in Zero-shot Reasoning Tasks
PDF
Code
IJCNLP-AACL 2025 Findings
[11]
FaithUn: Toward Faithful Forgetting in Language Models by Investigating the Interconnectedness of Knowledge
PDF
Code
EMNLP 2025
EMNLP 2025
CIKM 2025 (Oral)
2024
[8]
MVMR: A New Framework for Evaluating Faithfulness of Video Moment Retrieval against Multiple Distractors
PDF
Code
CIKM 2024 (Oral)
ACL 2024
PAKDD 2024 (Oral)
2023
EACL 2023 Findings
[4]
Multi-View Zero-Shot Open Intent Induction from Dialogues: Multi Domain Batch and Proxy Gradient Transfer
PDF
SIGDial 2023 Workshop (DSTC 11)
2022
ICASSP 2022 (Oral)
[2]
Semantic and Explainable Research-related Recommendation System based on Semi-supervised Methodology using BERT and LDA models
PDF
Expert Systems with Applications (2022)
2021
CIKM 2021
Education
-
Seoul National University
- Ph.D. in Artificial Intelligence, 2021–2026
- Advisor: Prof. Kyomin Jung
- Thesis: Knowledge Localization for Efficient and Safe Language Models PDF
- Distinguished Ph.D. Dissertation Award
-
Yonsei University
- M.S. in Industrial Engineering, 2019–2021
- Advisor: Prof. Wooju Kim
-
Ajou University
- Bachelor’s in Electronic Business / Software / Business Administration, 2015–2019
- Distinguished Graduate Award
Research Experience
-
Max Planck Institute for Software Systems (MPI-SWS)
- Postdoctoral Researcher, Jun 2026 – Current
- Advisors: Prof. Krishna P. Gummadi & Prof. Meeyoung Cha
- Topics: NLP, Interpretability, AI Safety
-
Max Planck Institute for Security and Privacy (MPI-SP)
- Research Intern, Aug 2025 – Oct 2025
- Working with Prof. Meeyoung Cha
- Topics: AI Safety, Pretraining · ICLR 2026[15,16], ACL 2026[18]
-
Adobe Research
- Collaborative Researcher, Feb 2023 – Jul 2025 (Funded by Research Gift)
- Remote working with Dr. David Seunghyun Yoon
- Topics: Multi-modality, AI Safety · CIKM 2024[8], EMNLP 2025[11]
-
LG AI Research
- Research Intern, Sep 2023 – Feb 2024
- Working with Prof. Honglak Lee & Dr. Jungkyu Choi
- Topics: AI Safety, LLM Application (EXAONE) · ACL 2024[7]