@article{coevalrankinglanguagemodelsforcustomtask,
  title = {CoEval: Ranking Language Models for Custom Tasks Without Labeled Data or Trustworthy Benchmarks},
  author = {Alexander Apartsin and Yehudit Aperstein},
  year = {2026},
  eprint = {2606.03650},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2606.03650},
}