NLSR: Neuron-Level Safety Realignment of Large Language Models Against Harmful Fine-Tuning

Yi et al. "NLSR: Neuron-Level Safety Realignment of Large Language Models Against Harmful Fine-Tuning." AAAI Conference on Artificial Intelligence, 2025. doi:10.1609/AAAI.V39I24.34762

[Yi et al. "NLSR: Neuron-Level Safety Realignment of Large Language Models Against Harmful Fine-Tuning." AAAI Conference on Artificial Intelligence, 2025.](https://mlanthology.org/aaai/2025/yi2025aaai-nlsr/) doi:10.1609/AAAI.V39I24.34762

@inproceedings{yi2025aaai-nlsr,
  title     = {{NLSR: Neuron-Level Safety Realignment of Large Language Models Against Harmful Fine-Tuning}},
  author    = {Yi, Xin and Zheng, Shunfan and Wang, Linlin and de Melo, Gerard and Wang, Xiaoling and He, Liang},
  booktitle = {AAAI Conference on Artificial Intelligence},
  year      = {2025},
  pages     = {25706-25714},
  doi       = {10.1609/AAAI.V39I24.34762},
  url       = {https://mlanthology.org/aaai/2025/yi2025aaai-nlsr/}
}