Chain-of-Thought CoT

Prompting a model to work through its reasoning step by step before answering, which measurably improves multi-step problems.

Natural Language Intermediate 1 min read

Also known as: CoT

Definition

Chain-of-thought prompting asks the model to show intermediate reasoning rather than jumping to an answer. On arithmetic, logic and multi-step questions this reliably improves accuracy, because each generated step conditions the next — the model gets to use its own output as working memory.

An important caveat: the stated reasoning is not a faithful trace of the computation. A model can produce sound-looking steps and a wrong answer, or the right answer via steps that do not support it. Treat it as a technique that improves accuracy, not as an explanation.

How it relates to other terms

Part of Prompt Engineering Writing the input to a model deliberately — with context, examples and constraints — to get a more reliable ou... See also Hallucination When a model states something false with the same fluency and confidence it uses for things that are true.
Referenced by
Prompt Engineering See also

Related terms

Large Language Model

LLM

A neural network trained on very large amounts of text to predict what comes next, which turns out to be enough to answer questions, write code and ho...

Beginner Natural Language

Token

The unit a language model actually reads and writes — usually a word fragment rather than a word or a character.

Beginner Natural Language

Context Window

The maximum number of tokens a model can consider at once — everything it is allowed to "see" for a single response.

Beginner Natural Language

Was this definition helpful?

Definitions are reviewed by our editorial team. Spotted a problem? Tell us.

Keep reading

Browse the glossary Suggest a correction