AI engineering glossary · LLM training alignment
What is weak-to-strong generalisation?
Weak-to-strong generalisation: A research setting that asks whether a strong model trained on labels from a weaker supervisor can perform better than the supervisor itself. It serves as an analogy for humans supervising future systems smarter than they are.
Weak-to-strong generalisation: an example
A small model's noisy labels are used to fine-tune a much larger model, and researchers check whether the large model beats its teacher.
Related terms
More LLM training alignment terms
Where you learn it
Weak-to-strong generalisation is part of the AI Engineering Program, which teaches it with notes, a hands-on lab and an exam. The first lesson is free.