@article{debatableintelligencebenchmarkingllm,
  title = {Debatable Intelligence: Benchmarking LLM Judges via Debate Speech Evaluation},
  author = {Noy Sternlicht and Ariel Gera and Roy Bar-Haim and Tom Hope and Noam Slonim},
  year = {2025},
  eprint = {2506.05062},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2506.05062v1},
}