Zhang X, Zhao Z, Shi W, Xu K, Huang D, Hu X. Safety Alignment of Large Language Models via Contrasting Safe and Harmful Distributions. AAAI [Internet]. 2026 Mar. 14 [cited 2026 May 16];40(41):34827-35. Available from: https://ojs.aaai.org/index.php/AAAI/article/view/40785