@article{evaluatinglanguagemodelsformathematics,
  title = {Evaluating Language Models for Mathematics through Interactions},
  author = {Katherine M. Collins and Albert Q. Jiang and Simon Frieder and Lionel Wong and Miri Zilka and Umang Bhatt and Thomas Lukasiewicz and Yuhuai Wu and Joshua B. Tenenbaum and William Hart and Timothy Gowers and Wenda Li and Adrian Weller and Mateja Jamnik},
  year = {2023},
  eprint = {2306.01694},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2306.01694v2},
}