Easy Prompting Question 29 of 223

What is chain-of-thought prompting?

GenAI / LLM · Speak this in 60–90 seconds · Faridabad & Delhi NCR

PICTURE THIS: A SENTENCE BECOMES TOKENS

The model does not read letters like humans. It reads these pieces, then predicts the next one.

Simple meaning

Chain-of-thought prompting asks the model to reason step by step before the final answer.

WHY — Tokens instead of words?

LLMs use tokens (not full words) because it helps them:

Prompting questions separate people

who only read docs from people who shipped.

Keep it short, concrete,

and tied to GenAI / LLM work.

Stable token IDs

Each piece maps to a number the network can learn.

Fits the model

Fixed pieces are what transformers expect as input.

STEPS — What happens with tokens?

Before the model can read a sentence, it goes through these steps:

1
Chain-of-thought prompting asks the
model to reason step by step before the final answer.
2
Extra intermediate tokens often
improve math, logic, and multi-hop questions.
3
You can hide the
reasoning from the user and show only the conclusion.
4
Context mix
Attention looks at nearby tokens together.
5
Next token
The model scores what should come next.
6
Decode
IDs turn back into readable text.

EXAMPLE — See it in action

Let's see how a real sentence is tokenized (tokens may vary by model):

Input text

“Extra intermediate tokens often improve math, logic, and multi-hop questions.”

Tokenized output

Extraintermediatetokensoftenimprovemath

Token IDs (example)

2987408337471632900

Note: Actual tokens and IDs depend on the tokenizer (e.g., GPT, Llama, etc.).

Key takeaway

Chain-of-thought prompting asks the model to reason step by step before the final answer. Extra intermediate tokens often improve math, logic, and multi-hop questions.