@article{confidentcalibratedorcomplicitsafetyalig,
  title = {Confident, Calibrated, or Complicit: Safety Alignment and Ideological Bias in LLM Hate Speech Detection},
  author = {Sanjeeevan Selvaganapathy and Mehwish Nasim},
  year = {2025},
  eprint = {2509.00673},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2509.00673},
}