ZHANG, Xiaoyun; ZHAO, Zhengyue; SHI, Wenxuan; XU, Kaidi; HUANG, Di; HU, Xing. Safety Alignment of Large Language Models via Contrasting Safe and Harmful Distributions. Proceedings of the AAAI Conference on Artificial Intelligence, [S. l.], v. 40, n. 41, p. 34827–34835, 2026. DOI: 10.1609/aaai.v40i41.40785. Disponível em: https://ojs.aaai.org/index.php/AAAI/article/view/40785. Acesso em: 16 may. 2026.