Intermediate5 min read29 of 52

Chain of Thought

Prompting the model to show step-by-step reasoning before answering, dramatically improving accuracy on complex tasks.

SPEC: Chain of Thought (CoT)

Definition

[Definition] Chain of Thought (CoT) prompting is a technique that encourages an LLM to produce intermediate reasoning steps before arriving at a final answer. By "thinking out loud," the model decomposes complex problems into manageable steps, dramatically improving accuracy on tasks requiring multi-step reasoning.

The Core Discovery

Introduced in the paper "Chain-of-Thought Prompting Elicits Reasoning in Large Language Models" (Wei et al., Google Brain, 2022).

Without CoT:

Q: A store sells 10 apples at $0.50 each and 5 oranges at $0.75 each. What's the total? A: $5.75 (often wrong without reasoning)

With CoT:

Q: A store sells 10 apples at $0.50 each and 5 oranges at $0.75 each. What's the total? A: Let me calculate step by step. Apples: 10 × $0.50 = $5.00 Oranges: 5 × $0.75 = $3.75 Total: $5.00 + $3.75 = $8.75 Answer: $8.75

Types of CoT Prompting

1. Few-Shot CoT (Original)

Provide examples that include reasoning chains:

Q: [Example problem] A: [Step-by-step reasoning] → [Answer] Q: [Example problem 2] A: [Step-by-step reasoning] → [Answer] Q: [New problem] A:

2. Zero-Shot CoT

Simply append a trigger phrase — no examples needed:

Q: [Problem] A: Let's think step by step.

Effective trigger phrases:

  • "Let's think step by step."
  • "Think carefully before answering."
  • "Let's work through this systematically."
  • "First, let me break this down."

3. Auto-CoT

Automatically generate reasoning chains using the model itself, then use those as few-shot examples.

4. Self-Consistency CoT

  1. Generate N independent reasoning chains (with temperature > 0)
  2. Each chain may reach a different answer
  3. Take the majority vote answer
  4. More reliable than single-chain CoT

5. Tree of Thoughts (ToT)

  • Extend CoT into a tree structure
  • Model explores multiple reasoning branches simultaneously
  • Backtrack from dead ends
  • Best path is selected via search/evaluation

When CoT Helps Most

Task TypeBenefit
Multi-step arithmeticHigh
Symbolic reasoningHigh
Logic puzzlesHigh
Commonsense reasoningModerate-High
Code debuggingHigh
Multi-hop QAHigh
Simple factual QALow (may hurt by adding noise)
ClassificationLow-Moderate

Mechanism: Why CoT Works

  1. Scratchpad effect: intermediate steps serve as working memory the model can reference
  2. Error decomposition: each small step is easier than the full problem
  3. Self-checking: making steps explicit creates opportunities to catch errors
  4. Attention shaping: reasoning tokens in the output condition subsequent token predictions

[Key Insight] Key insight: the tokens in the reasoning chain are real computation — they literally influence what the model outputs next.

CoT and Model Scale

CoT is an emergent ability — it only works well on sufficiently large models:

  • < 10B params: minimal benefit
  • ~10–50B params: moderate benefit
  • 100B params: strong benefit

  • Smaller models trained with CoT data can learn this skill (distillation)

Modern LLMs and "Thinking" Tokens

Frontier models (OpenAI o1, Claude 3.5+, Gemini Thinking) implement extended CoT via dedicated thinking/reasoning tokens that are generated before the final answer:

  • Hidden from the user (internal scratchpad)
  • Can be thousands of tokens of intermediate reasoning
  • Dramatically improves complex reasoning benchmarks
  • Referred to as "extended thinking" or "reasoning models"

CoT in Practice

Prompt Pattern

You are a math tutor. When solving problems, always show your reasoning step by step. For each step, explain why you're taking that step. Problem: [user's problem] Let me work through this step by step:

With Output Parsing

For structured output, separate the chain from the answer:

Reasoning: [full chain of thought] Final Answer: [just the answer]

Limitations

LimitationNotes
Hallucinated reasoningModel can produce fluent but wrong reasoning chains
CostReasoning tokens consume context and increase latency
Not always betterSimple tasks → CoT adds noise, not signal
Scale dependencyWeak on small models
Faithfulness questionReasoning may not reflect actual computation

Related Concepts

  • Few-Shot, Zero-Shot, Prompt, Inference, Reasoning Models, Tree of Thoughts, Self-Consistency