Eojin Joo, Chae-Gyun Lim, Jeongyun Han, Ho-Jin Choi. An Analysis of Unsafe Responses with Magic Expressions across Large Language Models. In IEEE International Conference on Big Data and Smart Computing, BigComp 2025, Kota Kinabalu, Malaysia, February 9-12, 2025. pages 406-409, IEEE, 2025. [doi]
Abstract is missing.