CUI, S.; FENG, X.; WANG, Y.; YANG, J.; ZHANG, Z.; SIKDAR, B.; WANG, H.; QIU, H.; HUANG, M. When Smiley Turns Hostile: Interpreting How Emojis Trigger LLMs’ Toxicity. Proceedings of the AAAI Conference on Artificial Intelligence, [S. l.], v. 40, n. 36, p. 30431-30439, 2026. DOI: 10.1609/aaai.v40i36.40296. Disponível em: https://ojs.aaai.org/index.php/AAAI/article/view/40296. Acesso em: 29 apr. 2026.