@article{aisandbagginglanguagemodelscan,
  title = {AI Sandbagging: Language Models can Strategically Underperform on Evaluations},
  author = {Teun van der Weij and Felix Hofstätter and Ollie Jaffe and Samuel F. Brown and Francis Rhys Ward},
  year = {2024},
  eprint = {2406.07358},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2406.07358v4},
}