@article{beyondperplexityutf8validityinbyteawarel, title = {Beyond Perplexity: UTF-8 Validity in Byte-aware Language Models}, author = {Sangwhan Moon and Daisuke Oba and Youmi Ma and Tatsuya Hiraoka and Naoaki Okazaki}, year = {2026}, eprint = {2606.14122}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2606.14122}, }