@inproceedings{singhal-etal-2026-tokenization, title = "Tokenization as Structural Inductive Bias: Grapheme-Constrained Subwords for Multilingual Modeling and Vocabulary Surgery", author = "Singhal, Arush and Bedi, Jatin and Singh, Jasmeet", editor = "Lee, Hung-Yi and Dev, Sunipa and Li, Jessy and Elliott, Desmond", booktitle = "Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing", month = oct, year = "2026", address = "Budapest, Hungary", publisher = "Association for Computational Linguistics", url = "https://aclanthology.org/2026.emnlp-main.972/", pages = "22414--22434", ISBN = "979-8-89176-459-0" }