@article{turninglogicagainstitselfprobingmodel,
  title = {Turning Logic Against Itself : Probing Model Defenses Through Contrastive Questions},
  author = {Rachneet Sachdeva and Rima Hazra and Iryna Gurevych},
  year = {2025},
  eprint = {2501.01872},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2501.01872v2},
}