@inproceedings{moniri-etal-2025-evaluating, title = "Evaluating the Performance of Large Language Models via Debates", author = "Moniri, Behrad and Hassani, Hamed and Dobriban, Edgar", editor = "Chiruzzo, Luis and Ritter, Alan and Wang, Lu", booktitle = "Findings of the Association for Computational Linguistics: NAACL 2025", month = apr, year = "2025", address = "Albuquerque, New Mexico", publisher = "Association for Computational Linguistics", url = "https://preview.aclanthology.org/fix-sig-urls/2025.findings-naacl.109/", pages = "2040--2075", ISBN = "979-8-89176-195-7" }