In-Place Tokenizer Expansion for Pre-trained LLMs
A tokenizer fixed at the start of pre-training allocates vocabulary in proportion to the pre-training corpus, reflecting the deployment priorities at that time. When those priorities shift, languages added later are split into many more tokens per word, which can raise latency, compute, and energy consumption for users of those languages. Cloud models can afford a broad vocabulary because the embedding and LM-head matrices are a small fraction of their parameters. On a compact model those matric
Record details
Published: 16 July 2026
Source: arXiv cs.AI
Category: Research
Topics: Environment
Retrieved: 18 July 2026
Related evidence
These records share source-supplied organisations, an exact publisher byline, automatic topics or regions. The reason is shown on every link; related does not mean supporting, agreeing with or verifying this record.
Can giant space mirrors boost green energy on Earth? A start-up aims to find out
Nature Machine Intelligence · 16 July 2026
Plover: Steering GUI Agents through Plan-Centric Interaction
arXiv cs.AI · 16 July 2026
The Industrialization of Research ; On AI-Driven Science and Its Consequences
arXiv cs.AI · 16 July 2026
Scaling Behavior Foundation Model for Humanoid Robots
arXiv cs.AI · 16 July 2026
Assessing Learning Processes with Multimodal Data in Virtual Reality Learning Environments
arXiv cs.HC · 16 July 2026
NIFA: Nonlinear IMC enhanced FPGA for efficient ML inference
arXiv cs.AI · 16 July 2026
How to cite this record
ethics.ai (16 July 2026), “In-Place Tokenizer Expansion for Pre-trained LLMs,” evidence record 11590, https://ethics.ai/record/11590 (originally published by arXiv cs.AI).
Use and limitations
This page is a stable index and citation surface for a source record. ethics.ai did not author the underlying report and has not independently verified every claim. Automatic topics may be imperfect. For consequential use, quote and cite the original publisher.