@article{safetyanalystinterpretabletransparentand,
  title = {SafetyAnalyst: Interpretable, Transparent, and Steerable Safety Moderation for AI Behavior},
  author = {Jing-Jing Li and Valentina Pyatkin and Max Kleiman-Weiner and Liwei Jiang and Nouha Dziri and Anne G. E. Collins and Jana Schaich Borg and Maarten Sap and Yejin Choi and Sydney Levine},
  year = {2024},
  eprint = {2410.16665},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2410.16665v3},
}