Technique
aka CoT
Chain of Thought
Prompting strategy that asks the model to reason step-by-step before answering.
Definition
Chain-of-thought prompting elicits intermediate reasoning steps from an LLM, dramatically improving accuracy on math, logic and multi-hop questions. Variants include zero-shot CoT ('Let's think step by step'), few-shot CoT and reasoning-tuned models that emit a hidden thinking trace.
Common use cases
- Math
- Logic puzzles
- Multi-hop QA