---
title: "Chain-of-Thought Prompting Elicits Reasoning in Large Language Models"
description: "This paper asks why showing a language model a few worked examples of step-by-step reasoning unlocks problems that direct prompting cannot touch. Read it to see how eight hand-written exemplars lifted PaLM 540B from 17.9% to 56.9% on grade-school math, why meaningless filler tokens explain none of the gain, and why the same prompt actively hurts smaller models."
canonical_url: "https://fanout.sh/daily/2026-08-18-chain-of-thought"
md_url: "https://fanout.sh/daily/2026-08-18-chain-of-thought.md"
last_updated: "2026-08-18"
access: "public"
---

# Chain-of-Thought Prompting Elicits Reasoning in Large Language Models

This paper asks why showing a language model a few worked examples of step-by-step reasoning unlocks problems that direct prompting cannot touch. Read it to see how eight hand-written exemplars lifted PaLM 540B from 17.9% to 56.9% on grade-school math, why meaningless filler tokens explain none of the gain, and why the same prompt actively hurts smaller models.

## Paper details

- Authors: Wei, Wang, Schuurmans, Bosma, Ichter, Xia, Chi, Le, and Zhou

- Venue: NeurIPS 2022

- Track: AI Research

- Difficulty: Easy

- Reading time: 30 min

- Original paper: https://arxiv.org/abs/2201.11903

## What you will learn

- How a few worked examples make a large model write its own intermediate steps before committing to an answer.

- Why the ablations show the gain comes from natural-language steps before the answer, not extra tokens or activated knowledge.

- Why the ability emerges only near hundred-billion-parameter scale, and what fluent but illogical chains do to smaller models.

## Continue exploring

[Explore chain-of-thought](https://fanout.sh/knowledge-graph?node=ai-research%3Aconcept%3Achain-of-thought-cot): Open Fanout's chain-of-thought concept in the knowledge graph and continue into in-context learning, emergent abilities, and the agent patterns that build on step-by-step reasoning.

---
This representation contains public Fanout content only. Protected Pro lessons, account data, billing, checkout, and pricing are not included.

Browse the public content map: https://fanout.sh/sitemap.md