@inproceedings{huidrom-belz-2025-using, title = "Using {LLM} Judgements for Sanity Checking Results and Reproducibility of Human Evaluations in {NLP}", author = "Huidrom, Rudali and Belz, Anya", editor = "Dhole, Kaustubh and Clinciu, Miruna", booktitle = "Proceedings of the Fourth Workshop on Generation, Evaluation and Metrics (GEM{\texttwosuperior})", month = jul, year = "2025", address = "Vienna, Austria and virtual meeting", publisher = "Association for Computational Linguistics", url = "https://preview.aclanthology.org/corrections-2025-08/2025.gem-1.30/", pages = "354--365", ISBN = "979-8-89176-261-9" }