AI engineering glossary · Prompt context engineering
What is least-to-most prompting?
Least-to-most prompting: A technique that first asks the model to break a hard problem into simpler sub-questions, then solves them in order, feeding earlier answers into later ones. It helps when the test problem is harder than the examples shown.
Least-to-most prompting: an example
A long word problem is split into 'How many boxes per truck?', then 'How many trucks?', then the final total.
Related terms
More Prompt context engineering terms
- Logit bias
- Logprobs
- Long-context prompting
- Lost in the middle
- Maieutic prompting
- Majority label bias
- Map-reduce summarisation
- Markdown formatting in prompts
Where you learn it
Least-to-most prompting is part of the AI Engineering Program, which teaches it with notes, a hands-on lab and an exam. The first lesson is free.