@article{positionstopevaluatingaiwithhumantestsde,
  title = {Position: Stop Evaluating AI with Human Tests, Develop Principled, AI-specific Tests instead},
  author = {Tom Sühr and Florian E. Dorner and Olawale Salaudeen and Augustin Kelava and Samira Samadi},
  year = {2025},
  eprint = {2507.23009},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2507.23009},
}