@inproceedings{cosma-etal-2026-training, title = "Training with Subword Variants Delays Overfitting in Repeated-Data Language Modeling", author = "Cosma, Adrian and Ruseti, Stefan and Radoi, Emilian and Dascalu, Mihai", editor = "Lee, Hung-Yi and Dev, Sunipa and Li, Jessy and Elliott, Desmond", booktitle = "Findings of the {A}ssociation for {C}omputational {L}inguistics: {EMNLP} 2026", month = oct, year = "2026", address = "Budapest, Hungary", publisher = "Association for Computational Linguistics", url = "https://aclanthology.org/2026.findings-emnlp.2157/", pages = "46144--46158", ISBN = "979-8-89176-462-0" }