SHI, H.; WANG, G.; OUYANG, T.; WANG, A. EASE: Practical and Efficient Safety Alignment for Small Language Models. Proceedings of the AAAI Conference on Artificial Intelligence, [S. l.], v. 40, n. 44, p. 37923-37931, 2026. DOI: 10.1609/aaai.v40i44.41129. Disponível em: https://ojs.aaai.org/index.php/AAAI/article/view/41129. Acesso em: 3 may. 2026.