@conference{SimPanJinSch26,
  title = {Training with Honeypots: Reshaping How LLMs Fail},
  booktitle = {ICLR 2026 Workshop on Principled Design for Trustworthy AI - Interpretability, Robustness, and Safety across Modalities},
  month = apr,
  year = {2026},
  author = {Simko, S. and Pandey, P. S. and Jin, Z. and Sch{\"o}lkopf, B.},
  url = {https://openreview.net/forum?id=yP24gVeeFo},
  month_numeric = {4}
}