Language-Specific Effects of Tokenizer Choice in Multilingual Language Models

arXiv:2610.12144 · cs.CL · Submitted 2026-10-08 · Read on arXiv

cs.CL

Submitted: 2026-10-08

Updated: 2026-10-08

Code: https://github.com/karpathy/nanochat

Terminology

• Accuracy — 39× in this paper · explained in 1 episode
• Benchmark — 19× in this paper · explained in 2 episodes
• Tokenization — 12× in this paper · explained in 2 episodes
• Embeddings — 11× in this paper · explained in 2 episodes
• Ablation — 6× in this paper · explained in 1 episode
• Low-Resource Languages — 6× in this paper · explained in 4 episodes
• Empirical Methods in Natural Language Processing — 5× in this paper
• Robustness — 5× in this paper · explained in 5 episodes
• Transformer — 5× in this paper · explained in 2 episodes
• Alignment — 3× in this paper · explained in 1 episode
• Adam — 2× in this paper · explained in 2 episodes
• Adaptation — 1× in this paper · explained in 1 episode
• Clustering — 1× in this paper · explained in 2 episodes
• Consistency — 1× in this paper · explained in 3 episodes
• Cross-lingual Transfer — 1× in this paper · explained in 2 episodes
• Domain Adaptation — 1× in this paper · explained in 5 episodes
• Downstream Tasks — 1× in this paper · explained in 2 episodes
• Entanglement — 1× in this paper · explained in 3 episodes
• Generalization — 1× in this paper · explained in 13 episodes
• International Conference on Machine Learning — 1× in this paper
• Large Language Model (LLM) — 1× in this paper · explained in 3 episodes
• Regularization — 1× in this paper · explained in 3 episodes

Sources

• TokSuite: Measuring the Impact of Tokenizer Choice on Language Model Behavior
• Evaluating Morphological Alignment of Tokenizers in 70 Languages
• MorphBPE: A Morpho-Aware Tokenizer Bridging Linguistic Complexity for Efficient LLM Training Across Morphologies
• Getting the most out of your tokenizer for pre-training and domain adaptation
• The Pile: An 800GB Dataset of Diverse Text for Language Modeling
• MinGram: A Minimalist Unigram Tokenizer with High Compression and Competitive Morphological Alignment
• BPE Stays on SCRIPT: Structured Encoding for Robust Multilingual Pretokenization
• SuperBPE: Space Travel for Language Models
• Tokenization counts: the impact of tokenization on arithmetic in frontier LLMs

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