@article{safeintshieldinglargelanguagemodelsfrom,
  title = {SafeInt: Shielding Large Language Models from Jailbreak Attacks via Safety-Aware Representation Intervention},
  author = {Jiaqi Wu and Chen Chen and Chunyan Hou and Xiaojie Yuan},
  year = {2025},
  eprint = {2502.15594},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2502.15594v1},
}