Cui, S., Feng, X., Wang, Y., Yang, J., Zhang, Z., Sikdar, B., Wang, H., Qiu, H. and Huang, M. (2026) “When Smiley Turns Hostile: Interpreting How Emojis Trigger LLMs’ Toxicity”, Proceedings of the AAAI Conference on Artificial Intelligence, 40(36), pp. 30431-30439. doi: 10.1609/aaai.v40i36.40296.