@article{whenjudgmentbecomesnoisehowdesignfailure,
  title = {When Judgment Becomes Noise: How Design Failures in LLM Judge Benchmarks Silently Undermine Validity},
  author = {Benjamin Feuer and Chiung-Yi Tseng and Astitwa Sarthak Lathe and Oussama Elachqar and John P Dickerson},
  year = {2025},
  eprint = {2509.20293},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2509.20293},
}