The Invisible Language Tax: Token Premiums of French and Regional Languages in 2026 LLM Tokenizers, and a French-Optimized Prototype

arXiv:2609.39001 · cs.CL, cs.AI · Submitted 2026-09-30 · Read on arXiv

cs.CL, cs.AI

Submitted: 2026-09-30

Updated: 2026-09-30

Code: https://github.com/Baracoda-ai-labs/baracoda-fr

Terminology

• Benchmark — 8× in this paper · explained in 2 episodes
• Tokenization — 8× in this paper · explained in 2 episodes
• Accuracy — 2× in this paper · explained in 1 episode
• Adaptation — 1× in this paper · explained in 1 episode
• Alignment — 1× in this paper · explained in 1 episode
• Embeddings — 1× in this paper · explained in 2 episodes
• Generalization — 1× in this paper · explained in 13 episodes
• Generative AI — 1× in this paper · explained in 2 episodes
• Large Language Model (LLM) — 1× in this paper · explained in 3 episodes
• Systematic Bias — 1× in this paper · explained in 3 episodes

Sources

• Language Model Tokenizers Introduce Unfairness Between Languages
• The Token Tax: Systematic Bias in Multilingual Tokenization
• Measuring the Tokenization Premium: A Cost Audit for Underserved Language Communities
• M-GATE: Multilingual Grammar, Accuracy in Translation, and Efficiency Benchmark for Large Language Models
• Lost in Compression: A Controlled Cross-Lingual Audit of Extractive Prompt Compressors
• Chinese Language Is Not More Efficient Than English in Vibe Coding: A Preliminary Study on Token Cost and Problem-Solving Rate
• CroissantLLM: A Truly Bilingual French-English Language Model
• Parity-Aware Byte-Pair Encoding: Improving Cross-lingual Fairness in Tokenization
• SuperBPE: Space Travel for Language Models
• SupraTok: Cross-Boundary Tokenization for Enhanced Language Model Performance
• FOCUS: Effective Embedding Initialization for Monolingual Specialization of Multilingual Models
• TokAlign: Efficient Vocabulary Adaptation via Token Alignment
• Gemma 3 Technical Report

Related papers

• Exploring Solution Divergence and Its Effect on Large Language Model Problem Solving
• Ishigaki-IDS-Bench: A Benchmark for Generating Information Delivery Specification from BIM Information Requirements
• Subliminal Steering: Stronger Encoding of Hidden Signals
• MedStruct-S: A Benchmark for Key Discovery, Key-Conditioned QA and Semi-Structured Extraction from OCR Clinical Reports
• The End of Transformers? On Challenging Attention and the Rise of Sub-Quadratic Architectures
• Untangling the Mechanisms of Misleading Context in Medical Question Answering