@article{anexpandedmassivemultilingualdatasetfor, title = {An Expanded Massive Multilingual Dataset for High-Performance Language Technologies}, author = {Laurie Burchell and Ona de Gibert and Nikolay Arefyev and Mikko Aulamo and Marta Bañón and and Pinzhen Chen and Mariia Fedorova and Liane Guillou and Barry Haddow and Jan Hajič and and Jindřich Helcl and Erik Henriksson and Mateusz Klimaszewski and Ville Komulainen and and Andrey Kutuzov and Joona Kytöniemi and Veronika Laippala and Petter Mæhlum and and Bhavitvya Malik and Farrokh Mehryary and Vladislav Mikhailov and Nikita Moghe and and Amanda Myntti and Dayyán O'Brien and Stephan Oepen and Proyag Pal and Jousia Piha and and Sampo Pyysalo and Gema Ramírez-Sánchez and David Samuel and Pavel Stepachev and and Jörg Tiedemann and Dušan Variš and Tereza Vojtěchová and Jaume Zaragoza-Bernabeu}, year = {2025}, eprint = {2503.10267}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2503.10267v1}, }