@article{deliberativealignmentisdeepbutuncertaint,
  title = {Deliberative Alignment is Deep, but Uncertainty Remains: Inference time safety improvement in reasoning via attribution of unsafe behavior to base model},
  author = {Pankayaraj Pathmanathan and Furong Huang},
  year = {2026},
  eprint = {2604.09665},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2604.09665},
}