@article{gptnlpubliccorpusapermissivelylicenseddu, title = {GPT-NL Public Corpus: A Permissively Licensed, Dutch-First Dataset for LLM Pre-training}, author = {Jesse van Oort and Frank Brinkkemper and Erik de Graaf and Bram Vanroy and Saskia Lensink}, year = {2026}, eprint = {2604.00920}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2604.00920}, }