YI, Xin; ZHENG, Shunfan; WANG, Linlin; DE MELO, Gerard; WANG, Xiaoling; HE, Liang. NLSR: Neuron-Level Safety Realignment of Large Language Models Against Harmful Fine-Tuning. Proceedings of the AAAI Conference on Artificial Intelligence, [S. l.], v. 39, n. 24, p. 25706–25714, 2025. DOI: 10.1609/aaai.v39i24.34762. Disponível em: https://ojs.aaai.org/index.php/AAAI/article/view/34762. Acesso em: 26 may. 2026.