@article{discoveringforbiddentopicsinlanguage,
  title = {Discovering Forbidden Topics in Language Models},
  author = {Can Rager and Chris Wendler and Rohit Gandikota and David Bau},
  year = {2025},
  eprint = {2505.17441},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2505.17441v2},
}