{"version.version":"0.1.1","version.cm_url":"https://github.com/ceurws/ceur-spt","spt.html_url":"/Vol-4240/paper45.html","spt.description":null,"spt.id":"Vol-4240/paper45","spt.wikidataid":null,"spt.title":"How Surprising Is Historical Italian to Language Models? Tokenization Tax, Comprehension Tax, and a Simple Mitigation","spt.pdfUrl":"https://ceur-ws.org/Vol-4240/paper45.pdf","spt.volume":{"number":4240,"acronym":"IRCDL 2026","wikidataid":"Q141603265","title":"Proceedings of the 22nd Conference on Information and Research Science Connecting to Digital and Library Science","description":"Proceedings of IRCDL 2026 workshop","url":"https://ceur-ws.org/Vol-4240/","date":"2026-08-20","dblp":null,"k10plus":null,"urn":"urn:nbn:de:0074-4240-x"},"spt.session":null,"cvb.id":"Vol-4240/paper45","cvb.title":"How Surprising Is Historical Italian to Language Models? Tokenization Tax, Comprehension Tax, and a Simple Mitigation","cvb.type":null,"cvb.position":null,"cvb.pagesFrom":null,"cvb.pagesTo":null,"cvb.authors":"Mariia Levchenko","cvb.pages":null,"cvb.vol_number":"4240","cvb.pdf_name":"paper45.pdf","cvb.fail":null}