Chain-of-Thought (CoT)

Chain-of-Thought prompting encourages models to break down complex problems into intermediate reasoning steps.

Simple Trigger: Adding "Let's think step by step" to prompts

Why It Works: - Forces explicit reasoning - Reduces errors in multi-step problems - Makes reasoning transparent - Improves mathematical and logical tasks

• **Variations:**
• Zero-shot CoT: Just add "think step by step"
• Few-shot CoT: Provide examples with reasoning
• Self-consistency: Generate multiple reasoning paths
• Tree-of-Thought: Branch and evaluate paths

When to Use: - Math problems - Logic puzzles - Complex reasoning - Multi-step instructions