SafetyPrompts: A Systematic Review of Open Datasets for Evaluating and Improving Large Language Model Safety

Cite

Text

Röttger et al. "SafetyPrompts: A Systematic Review of Open Datasets for Evaluating and Improving Large Language Model Safety." AAAI Conference on Artificial Intelligence, 2025. doi:10.1609/AAAI.V39I26.34975

Markdown

[Röttger et al. "SafetyPrompts: A Systematic Review of Open Datasets for Evaluating and Improving Large Language Model Safety." AAAI Conference on Artificial Intelligence, 2025.](https://mlanthology.org/aaai/2025/rottger2025aaai-safetyprompts/) doi:10.1609/AAAI.V39I26.34975

BibTeX

@inproceedings{rottger2025aaai-safetyprompts,
  title     = {{SafetyPrompts: A Systematic Review of Open Datasets for Evaluating and Improving Large Language Model Safety}},
  author    = {Röttger, Paul and Pernisi, Fabio and Vidgen, Bertie and Hovy, Dirk},
  booktitle = {AAAI Conference on Artificial Intelligence},
  year      = {2025},
  pages     = {27617-27627},
  doi       = {10.1609/AAAI.V39I26.34975},
  url       = {https://mlanthology.org/aaai/2025/rottger2025aaai-safetyprompts/}
}