Firestone, P., Ugare, S., Singh, G., & Misailovic, S. (2025). UTF-8 Plumbing: Byte-level Tokenizers Unavoidably Enable LLMs to Generate Ill-formed UTF-8.
Chicago Style (17th ed.) CitationFirestone, Preston, Shubham Ugare, Gagandeep Singh, and Sasa Misailovic. UTF-8 Plumbing: Byte-level Tokenizers Unavoidably Enable LLMs to Generate Ill-formed UTF-8. 2025.
MLA (9th ed.) CitationFirestone, Preston, et al. UTF-8 Plumbing: Byte-level Tokenizers Unavoidably Enable LLMs to Generate Ill-formed UTF-8. 2025.
Warning: These citations may not always be 100% accurate.