Prompt Engineering103 · Module I · Lesson 03 of 14
Article · 12 min

Chain-of-thought

When to ask for reasoning, and when not to.

Summary

Chain-of-thought (CoT): ask the model to reason step by step before answering. On math, logic, and multi-step tasks it improves accuracy by 10-40 percentage points. On simple tasks it wastes tokens. Learning when to use it is the discipline.

Objectives
  • 01State the chain-of-thought result.
  • 02Recognize tasks where CoT helps versus tasks where it does not.
  • 03Distinguish zero-shot CoT from few-shot CoT.
The Lesson

The result

Wei et al. 2022: adding 'Let's think step by step' or few-shot CoT examples improved GSM8K math accuracy from ~18% to ~57% with the same underlying model. The result generalizes to logic, planning, and multi-step reasoning.

When not to use it

Simple classification, lookup, or single-fact extraction — CoT wastes tokens and can degrade accuracy by overthinking. Modern reasoning models internalize CoT during RL; explicit CoT prompts are less useful with them.

Key Ideas
  • CoT trades tokens for accuracy on multi-step tasks.
  • Not a universal win; unnecessary on simple tasks.
References
  • Wei et al., 'Chain-of-Thought Prompting Elicits Reasoning in Large Language Models' (2022)