What is Chain-of-Thought?

Chain-of-Thought

Definition A prompting technique where the model is instructed or shown examples of reasoning step-by-step before giving a final answer, improving performance on complex reasoning, math, and multi-step tasks. Chain-of-thought prompting essentially asks the model to "show its work."

In Depth

Introduced in a 2022 Google paper, chain-of-thought prompting (CoT) demonstrated that large models can solve problems they fail on when prompted directly, simply by walking through intermediate steps. Variants include zero-shot CoT ("think step by step"), self-consistency (sampling multiple chains and majority-voting), and tree-of-thought (exploring branching reasoning paths). CoT is now standard practice for reasoning-heavy LLM applications.

Browse more terms

AI Agent AI Alignment Agentic AI Artificial General Intelligence Artificial Superintelligence Attention Mechanism AutoML Benchmark Bias (AI) Chain-of-Thought Computer Vision Deepfake Diffusion Model Edge AI Embedding Federated Learning Few-Shot Learning Fine-Tuning Function Calling GPT