HomeAI & MLAwesome NLP › The Token Tax: Systematic Bias in Multilingual Tokenization

The Token Tax: Systematic Bias in Multilingual Tokenization

arxiv.org ↗

(2025) - quantifies how tokenization fertility predicts model accuracy across languages, exposing structural cost penalties for morphologically complex and low-resource languages.

↵ to searchesc to close
awesomelist.dev