@article{agreementmetricsforllmasjudgeevaluationw, title = {Agreement Metrics for LLM-as-Judge Evaluation: What to Report and Why}, author = {Delip Rao and Chris Callison-Burch}, year = {2026}, eprint = {2606.00093}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2606.00093}, }