Nakyeong Yang

Postdoc, Seoul National University

PhD student, Seoul National University

Joined

January 2022

Names

Nakyeong Yang (Preferred)

Emails

****@snu.ac.kr (Confirmed)

****@gmail.com (Confirmed)

Personal Links

Career & Education History

Postdoc

Seoul National University (snu.ac.kr)

2026 – 2026

PhD student

Seoul National University (snu.ac.kr)

2021 – 2026

Advisors, Relations & Conflicts

PhD Advisor

Kyomin Jung

2021 – 2026

Expertise

interpretability

AI Safety

2023 – 2026

interpretability

natural language understanding

language model

2019 – 2024

Publications

Tool Selection Bias Amplifies in Multi-turn User–Agent Interactions
Nakyeong Yang, Junseok Kim, Kyomin Jung
- ICML 2026 AIWILD
- Readers: Everyone
Personalized Privacy Control in LLMs via Attention Head Intervention
Junseok Kim, Nakyeong Yang, Kyomin Jung
- ICML 2026 FoGen Workshop Poster
- Readers: Everyone
Bilinear representation mitigates reversal curse and enables consistent model editing
Dong-Kyum Kim, Minsung Kim, Jea Kwon, Nakyeong Yang, Meeyoung Cha
- ICLR 2026 Poster
- Readers: Everyone
Erase or Hide? Suppressing Spurious Unlearning Neurons for Robust Unlearning
Nakyeong Yang, Dong-Kyum Kim, Jea Kwon, Minsung Kim, Kyomin Jung, Meeyoung Cha
- ICLR 2026 Poster
- Readers: Everyone
Training Dynamics of Parametric and In-Context Knowledge Utilization in Language Models
Minsung Kim, Dong-Kyum Kim, Jea Kwon, Nakyeong Yang, Kyomin Jung, Meeyoung Cha
- ICLR 2026 Conference Withdrawn Submission
- Readers: Everyone
Knowledge-localized Unlearning for Faithful Forgetting in Language Models
Nakyeong Yang, Minsung Kim, Seunghyun Yoon, Joongbo Shin, Kyomin Jung
- Submitted to ICLR 2025
- Readers: Everyone
A New Framework for Evaluating Faithfulness of Video Moment Retrieval against Multiple Distractors
Nakyeong Yang, Minsung Kim, Seunghyun Yoon, Joongbo Shin, Kyomin Jung
- CIKM 2024
- Readers: Everyone
LongStory: Coherent, Complete and Length Controlled Long Story Generation
Kyeongman Park, Nakyeong Yang, Kyomin Jung
- PAKDD (2) 2024
- Readers: Everyone
Mitigating Biases for Instruction-following Language Models via Bias Neurons Elimination
Nakyeong Yang, Taegwan Kang, Stanley Jungkyu Choi, Honglak Lee, Kyomin Jung
- ACL (1) 2024
- Readers: Everyone
Task-specific Compression for Multi-task Language Models using Attribution-based Pruning
Nakyeong Yang, Yunah Jang, Hwanhee Lee, Seohyeong Jeong, Kyomin Jung
- Published: 01 Jan 2023, Last Modified: 29 Jan 2024
- EACL (Findings) 2023
- Readers: Everyone

View all 13 publications