I am an incoming graduate student at Korea Advanced Institute of Science and Technology (KAIST), advised by Prof. Kimin Lee. My current research focuses on distillation and RL based post-training for reasoning tasks in LLM. Previously, I worked on the safety and alignment of LLM agents.
[C2] Unintended Misalignment from Agentic Fine-Tuning: Risks and Mitigation
Dongyoon Hahm*, Taywon Min*, Woogyeol Jin*, Kimin Lee
AAAI Conference on Artificial Intelligence (AAAI), 2026
[C1] Enhancing LLM Agent Safety via Causal Influence Prompting
Dongyoon Hahm, Woogyeol Jin, Junesuk Choi, Sungsoo Ahn, Kimin Lee
Findings of the Association for Computational Linguistics (ACL Findings), 2025
[C2] Unintended Misalignment from Agentic Fine-Tuning: Risks and Mitigation
Dongyoon Hahm*, Taywon Min*, Woogyeol Jin*, Kimin Lee
AAAI Conference on Artificial Intelligence (AAAI), 2026
[C1] Enhancing LLM Agent Safety via Causal Influence Prompting
Dongyoon Hahm, Woogyeol Jin, Junesuk Choi, Sungsoo Ahn, Kimin Lee
Findings of the Association for Computational Linguistics (ACL Findings), 2025
Korea Advanced Institute of Science and Technology (KAIST)Mar. 2020 - Feb. 2026
B.S. in Computer Science / Electrical Engineering
Undergraduate Research InternSep. 2024 - Feb. 2026
Rise LabUndergraduate Research InternNov. 2023 - Mar. 2024
Computer Architecture and Systems Lab