Yi X, Zheng S, Wang L, de Melo G, Wang X, He L. NLSR: Neuron-Level Safety Realignment of Large Language Models Against Harmful Fine-Tuning. AAAI [Internet]. 2025 Apr. 11 [cited 2026 May 26];39(24):25706-14. Available from: https://ojs.aaai.org/index.php/AAAI/article/view/34762