@article{evaluationunderimperfectbenchmarksand,
  title = {Evaluation Under Imperfect Benchmarks and Ratings: A Case Study in Text Simplification},
  author = {Joseph Liu and Yoonsoo Nam and Xinyue Cui and Swabha Swayamdipta},
  year = {2025},
  eprint = {2504.09394},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2504.09394v2},
}