@article{acausalexplainableguardrailsforlarge,
  title = {A Causal Explainable Guardrails for Large Language Models},
  author = {Zhixuan Chu and Yan Wang and Longfei Li and Zhibo Wang and Zhan Qin and Kui Ren},
  year = {2024},
  eprint = {2405.04160},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2405.04160v2},
}