32 researchers spent 8 months on the most comprehensive survey of tokenization ever

christopher · x · 2026-10-01

A new paper argues that tokenization is a wildly understudied area of language modeling, despite its effects across all of NLP.

Over the past 8 months, 32 tokenizer researchers put together the most comprehensive survey of the field to date, covering how tokenization choices ripple through language models.

Original post →

More from Models

Models channel →