LLM Neologism: Emergence of Mutated Characters due to Byte Encoding

LLM Neologism: Emergence of Mutated Characters due to Byte Encoding Ran Iwamoto author Hiroshi Kanayama author 2024-09 text Proceedings of the 17th International Natural Language Generation Conference Saad Mahamood editor Nguyen Le Minh editor Daphne Ippolito editor Association for Computational Linguistics Tokyo, Japan conference publication iwamoto-kanayama-2024-llm-neologism 10.18653/v1/2024.inlg-main.3 https://aclanthology.org/2024.inlg-main.3/ 2024-09 24 29