@article{letthemodelsrespondinterpretinglanguage,
  title = {Let the Models Respond: Interpreting Language Model Detoxification Through the Lens of Prompt Dependence},
  author = {Daniel Scalena and Gabriele Sarti and Malvina Nissim and Elisabetta Fersini},
  year = {2023},
  eprint = {2309.00751},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2309.00751v1},
}