Minseok Choi
Postdoctoral Fellow, KAIST
minseok.choi [AT] kaist.ac.kr
About
Hi! I am a postdoctoral fellow at KAIST AI, supported by the InnoCORE Postdoctoral Fellowship, where I work with Jaegul Choo at the DAVIAN Lab. I am also fulfilling my military service as Technical Research Personnel in the Republic of Korea Army. My research focuses on large language models, particularly their safety and their use as autonomous agents. Previously, I was a research intern at Krafton and Naver Webtoon. I received my Ph.D. from KAIST and my B.S. in Computer Science from the University of Illinois at Urbana-Champaign.
I am always happy to chat about research, agents, or anything in between — feel free to reach out over email or coffee if you are around Seoul.
News
- [Feb 2026] Terminus-KIRA, a coding agent developed by our team at Krafton, reached 74.8% on Terminal-Bench, ranking #2 on the leaderboard (#1 with Opus 4.6).
- [Jan 2026] Our paper ExpGuard has been accepted to ICLR 2026!
- [Nov 2025] I have successfully defended my dissertation!
- [May 2025] Our paper Opt-Out has been accepted to ACL 2025!
- [May 2025] I will be joining Krafton as an Applied Research Intern this summer!
- [Sep 2024] Our paper LingTea has been accepted to EMNLP 2024 Findings!
- [Jul 2024] Our paper PairEval has been accepted to COLM 2024!
- [May 2024] Our paper POP has been accepted to ACL 2024 Findings!
- [Oct 2023] Our paper SimCKP has been accepted to EMNLP 2023 Findings!
- [May 2023] Our paper HistRED has been accepted to ACL 2023!
- [Mar 2023] I started my military service in the Republic of Korea Army as Technical Research Personnel.
- [Jan 2022] I will be joining Naver Webtoon as a Research Intern this winter!
Publications
( * indicates equal contributions.)
ExpGuard: LLM Content Moderation in Specialized Domains
Minseok Choi*, Dongjin Kim*, Seungbin Yang*, Subin Kim, Youngjun Kwak, Juyoung Oh, Jaegul Choo, Jungmin Son
ICLR 2026
DataBreaking Chains: Unraveling the Links in Multi-Hop Knowledge Unlearning
Minseok Choi, ChaeHun Park, Dohyun Lee, Jaegul Choo
Preprint
Opt-Out: Investigating Entity-Level Unlearning for Large Language Models via Optimal Transport
Minseok Choi, Daniel Rim, Dohyun Lee, Jaegul Choo
ACL 2025
Cross-Lingual Unlearning of Selective Knowledge in Multilingual Language Models
Minseok Choi, Kyunghyun Min, Jaegul Choo
EMNLP 2024 Findings
PairEval: Open-domain Dialogue Evaluation with Pairwise Comparison
ChaeHun Park, Minseok Choi, Dohyun Lee, Jaegul Choo
COLM 2024
Protecting Privacy Through Approximating Optimal Parameters for Sequence Unlearning in Language Models
Dohyun Lee*, Daniel Rim*, Minseok Choi, Jaegul Choo
ACL 2024 Findings
SimCKP: Simple Contrastive Learning of Keyphrase Representations
Minseok Choi, Chaeheon Gwak, Seho Kim, Si hyeong Kim, Jaegul Choo
EMNLP 2023 Findings
PRiSM: Enhancing Low-Resource Document-Level Relation Extraction with Relation-Aware Score Calibration
Minseok Choi, Hyesu Lim, Jaegul Choo
IJCNLP-AACL 2023 Findings
HistRED: A Historical Document-Level Relation Extraction Dataset
Soyoung Yang, Minseok Choi, Youngwoo Cho, Jaegul Choo
ACL 2023
Rethinking Style Transformer by Energy-based Interpretation: Adversarial Unsupervised Style Transfer using a Pretrained Model
Hojun Cho, Dohee Kim, Seungwoo Ryu, ChaeHun Park, Hyungjong Noh, Jeong-in Hwang, Minseok Choi, Edward Choi, Jaegul Choo
EMNLP 2022
Development and Application of Web‑based Machine Learning Program for Automated Assessment Model Generation
Minseok Choi, Jaegul Choo, Minsu Ha
Brain, Digital, & Learning, Vol. 12, No. 4, pp. 567-578, 2022
ExpGuard: LLM Content Moderation in Specialized Domains
Minseok Choi*, Dongjin Kim*, Seungbin Yang*, Subin Kim, Youngjun Kwak, Juyoung Oh, Jaegul Choo, Jungmin Son
ICLR 2026
Breaking Chains: Unraveling the Links in Multi-Hop Knowledge Unlearning
Minseok Choi, ChaeHun Park, Dohyun Lee, Jaegul Choo
Preprint
Opt-Out: Investigating Entity-Level Unlearning for Large Language Models via Optimal Transport
Minseok Choi, Daniel Rim, Dohyun Lee, Jaegul Choo
ACL 2025
Cross-Lingual Unlearning of Selective Knowledge in Multilingual Language Models
Minseok Choi, Kyunghyun Min, Jaegul Choo
EMNLP 2024 Findings
PairEval: Open-domain Dialogue Evaluation with Pairwise Comparison
ChaeHun Park, Minseok Choi, Dohyun Lee, Jaegul Choo
COLM 2024
Protecting Privacy Through Approximating Optimal Parameters for Sequence Unlearning in Language Models
Dohyun Lee*, Daniel Rim*, Minseok Choi, Jaegul Choo
ACL 2024 Findings
SimCKP: Simple Contrastive Learning of Keyphrase Representations
Minseok Choi, Chaeheon Gwak, Seho Kim, Si hyeong Kim, Jaegul Choo
EMNLP 2023 Findings
PRiSM: Enhancing Low-Resource Document-Level Relation Extraction with Relation-Aware Score Calibration
Minseok Choi, Hyesu Lim, Jaegul Choo
IJCNLP-AACL 2023 Findings
HistRED: A Historical Document-Level Relation Extraction Dataset
Soyoung Yang, Minseok Choi, Youngwoo Cho, Jaegul Choo
ACL 2023
Rethinking Style Transformer by Energy-based Interpretation: Adversarial Unsupervised Style Transfer using a Pretrained Model
Hojun Cho, Dohee Kim, Seungwoo Ryu, ChaeHun Park, Hyungjong Noh, Jeong-in Hwang, Minseok Choi, Edward Choi, Jaegul Choo
EMNLP 2022
Development and Application of Web‑based Machine Learning Program for Automated Assessment Model Generation
Minseok Choi, Jaegul Choo, Minsu Ha
Brain, Digital, & Learning, Vol. 12, No. 4, pp. 567-578, 2022
Vitæ
Full CV in PDF.
-
KAIST Mar 2026 - PresentPostdoctoral Fellow
Information & Electronics Research Institute -
Krafton May 2025 - Feb 2026
-
Republic of Korea Army Mar 2023 - PresentTechnical Research Personnel
Compulsory military service -
Naver Webtoon Jan-Jun 2022Research Intern
Keyphrase Extraction & Generation -
KAIST Mar 2020 - Feb 2026M.S.-Ph.D. Integrated Student (Advisor: Jaegul Choo)
Data and Visual Analytics Lab -
University of Illinois at Urbana-Champaign Sep 2017 - May 2019B.S. in Computer Science
with Honors