AI engineering glossary · LLM training alignment
What is task arithmetic?
Task arithmetic (also called Task vector): Editing a model by computing a task vector, the difference between fine-tuned and base weights, and adding, scaling or subtracting it from the base model to give or remove a skill.
Task arithmetic: an example
base + 0.5 * (math_finetuned - base) adds half of the maths skill to the base model.
Related terms
More LLM training alignment terms
- Teacher-student learning
- Tensor parallelism
- Test-time compute scaling
- Trust region policy optimisation
- UltraFeedback
- Value function
- Warmup-stable-decay schedule
- Weak-to-strong generalisation
Where you learn it
Task arithmetic is part of the AI Engineering Program, which teaches it with notes, a hands-on lab and an exam. The first lesson is free.