Papers

• Deontological Keyword Bias: The Impact of Modal Expressions on Normative Judgments of Language Models, Bumjin Park, Jinsil Lee, Jaesik Choi, Association for Computational Linguistics (ACL), 2025 [pdf]
• Memorizing Documents with Guidance in Large Language Models, Bumjin Park, Jaesik Choi, International Joint Conference on Artificial Intelligence (IJCAI), 2024 [pdf]
• Identifying the Source of Generation for Large Language Models, Bumjin Park, Jaesik Choi, Pattern Recognition and Artificial Intelligence. ICPRAI, 2024 [pdf]
• Message Action Adapter Framework in Multi-Agent Reinforcement Learning, Bumjin Park, Jaesik Choi, Applied Sciences, 2024 [pdf]
• [ MS Thesis] Partitioned Channel Gradient for Reliable Saliency Map in Image Classification, Bumjin Park, supervised by Jaesik Choi [📂 Drive]
• Cooperative multi-robot task allocation with reinforcement learning, Bumjin Park, Cheongwoong Kang, Jaesik Choi, Applied Sciences, 2021 [pdf]
• Scheduling PID attitude and position control frequencies for time-optimal quadrotor waypoint tracking under unknown external disturbances, Cheongwoong Kang, Bumjin Park, Jaesik Choi Sensors, 2021 [pdf]
• Generating Multi-agent Patrol Areas by Reinforcement Learning, Bumjin, Park , Cheongwoong Kang, and Jaesik Choi, 21st International Conference on Control, Automation and Systems (ICCAS), 2021 [pdf]

Preprint

• Representation Interpretation of Refusal Mechanism In Large Language Models, Bumjin Park, Yeonjea Kim, Jinsil Lee, Youngju Joung and Jaesik Choi [drive]
• Incomplete Prompt Jailbreak, Yeonjea Kim, Jinsil Lee, Bumjin Park, Youngju Joung and Jaesik Choi [drive]
• ParchGrad: Controlled Internal Gradients for Reliable Saliency Map, Bumjin Park , Giyoung Jeon, and Jaesik Choi [pdf]
• Explanation on Pretraining Bias of Finetuned Vision Transformer, Bumjin Park and Jaesik Choi. [pdf].