Loading…
Glossary term
A technique in which a model works through intermediate reasoning steps before giving a final answer.
Chain-of-thought prompting asks a model to write out intermediate steps before the final answer. Working through the problem in text improves accuracy on arithmetic, logic and multi-step questions.
Reasoning models now do this internally, often producing a long hidden or visible chain before answering.
Prompting for step-by-step reasoning
Q: A shop sells pens at 3 for $2. How much do 12 pens cost?
Think step by step.
A: 12 pens is 4 groups of 3. Each group costs $2, so 4 x $2 = $8.
Answer: $8It showed that how a model is asked to think can matter as much as its size, and led to reasoning models.