Eugene Jang, Kimin Lee, Jin-Woo Chung, Keuntae Park, Seungwon Shin 0001. Improbable Bigrams Expose Vulnerabilities of Incomplete Tokens in Byte-Level Tokenizers. In Christos Christodoulopoulos 0001, Tanmoy Chakraborty 0002, Carolyn Rose, Violet Peng, editors, Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing, EMNLP 2025, Suzhou, China, November 4-9, 2025. pages 18209-18216, Association for Computational Linguistics, 2025. [doi]
@inproceedings{JangLCPS25,
title = {Improbable Bigrams Expose Vulnerabilities of Incomplete Tokens in Byte-Level Tokenizers},
author = {Eugene Jang and Kimin Lee and Jin-Woo Chung and Keuntae Park and Seungwon Shin 0001},
year = {2025},
doi = {10.18653/v1/2025.emnlp-main.919},
url = {https://doi.org/10.18653/v1/2025.emnlp-main.919},
researchr = {https://researchr.org/publication/JangLCPS25},
cites = {0},
citedby = {0},
pages = {18209-18216},
booktitle = {Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing, EMNLP 2025, Suzhou, China, November 4-9, 2025},
editor = {Christos Christodoulopoulos 0001 and Tanmoy Chakraborty 0002 and Carolyn Rose and Violet Peng},
publisher = {Association for Computational Linguistics},
isbn = {979-8-89176-332-6},
}