Go Inoue, Bashar Alhafni, Nizar Habash, Timothy Baldwin. Do Diacritics Matter? Evaluating the Impact of Arabic Diacritics on Tokenization and LLM Benchmarks. In Vera Demberg, Kentaro Inui, Lluís Marquez, editors, Findings of the Association for Computational Linguistics: EACL 2026, Rabat, Morocco, March 24-29, 2026. pages 426-442, Association for Computational Linguistics, 2026. [doi]
@inproceedings{InoueAHB26,
title = {Do Diacritics Matter? Evaluating the Impact of Arabic Diacritics on Tokenization and LLM Benchmarks},
author = {Go Inoue and Bashar Alhafni and Nizar Habash and Timothy Baldwin},
year = {2026},
url = {https://aclanthology.org/2026.findings-eacl.22/},
researchr = {https://researchr.org/publication/InoueAHB26},
cites = {0},
citedby = {0},
pages = {426-442},
booktitle = {Findings of the Association for Computational Linguistics: EACL 2026, Rabat, Morocco, March 24-29, 2026},
editor = {Vera Demberg and Kentaro Inui and Lluís Marquez},
publisher = {Association for Computational Linguistics},
isbn = {979-8-89176-386-9},
}