@article{beyondaccuracyevaluatingthereasoning,
  title = {Beyond Accuracy: Evaluating the Reasoning Behavior of Large Language Models -- A Survey},
  author = {Philipp Mondorf and Barbara Plank},
  year = {2024},
  eprint = {2404.01869},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2404.01869v2},
}