activity
20202026
most citedLLM-jp: A Cross-organizational Project for the Research and Development of Fully Open Japanese LLMs

5 citations · 7 across the 10 of their papers we have counts for

collaborators

11 papers

cs.CL2026

Beyond Perplexity: UTF-8 Validity in Byte-aware Language Models

Sangwhan Moon, Daisuke Oba, Youmi Ma +2

Byte-level tokenization enables language models to handle any Unicode input, but models can generate invalid UTF-8 sequences when encountering rare or unseen characters. We investi…

cs.CL2025

Bit-level BPE: Below the byte boundary

Sangwhan Moon, Tatsuya Hiraoka, Naoaki Okazaki

Byte-level fallbacks for subword tokenization have become a common practice in large language models. In particular, it has been demonstrated to be incredibly effective as a pragma…

cs.CL2024★ 5 cited

LLM-jp: A Cross-organizational Project for the Research and Development of Fully Open Japanese LLMs

LLM-jp, :, Akiko Aizawa +80

This paper introduces LLM-jp, a cross-organizational project for the research and development of Japanese large language models (LLMs). LLM-jp aims to develop open-source and stron…

cs.CL2024

An Analysis of BPE Vocabulary Trimming in Neural Machine Translation

Marco Cognetta, Tatsuya Hiraoka, Naoaki Okazaki +2

We explore threshold vocabulary trimming in Byte-Pair Encoding subword tokenization, a postprocessing step that replaces rare subwords with their component subwords. The technique…

cs.CL2024

Knowledge of Pretrained Language Models on Surface Information of Tokens

Tatsuya Hiraoka, Naoaki Okazaki

Do pretrained language models have knowledge regarding the surface information of tokens? We examined the surface information stored in word or subword embeddings acquired by pretr…

cs.CL2023

Downstream Task-Oriented Neural Tokenizer Optimization with Vocabulary Restriction as Post Processing

Tatsuya Hiraoka, Tomoya Iwakura

This paper proposes a method to optimize tokenization for the performance improvement of already trained downstream models. Our method generates tokenization results attaining lowe…