@inproceedings{saleva-etal-2025-beyond, title = "Beyond statistical significance: Quantifying uncertainty and statistical variability in multilingual and multitask {NLP} evaluation", author = {S{\"a}lev{\"a}, Jonne and Ataman, Duygu and Lignos, Constantine}, editor = "Inui, Kentaro and Sakti, Sakriani and Wang, Haofen and Wong, Derek F. and Bhattacharyya, Pushpak and Banerjee, Biplab and Ekbal, Asif and Chakraborty, Tanmoy and Singh, Dhirendra Pratap", booktitle = "Proceedings of the 14th International Joint Conference on Natural Language Processing and the 4th Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics", month = dec, year = "2025", address = "Mumbai, India", publisher = "The Asian Federation of Natural Language Processing and The Association for Computational Linguistics", url = "https://preview.aclanthology.org/ingest-ijcnlp-aacl/2025.ijcnlp-long.125/", pages = "2304--2321", ISBN = "979-8-89176-298-5" }