A field guide to AI positions

Chain of thought (CoT)

Publication dates and source age

Sources counted: 3

Newest dated source: 2025-04-03

At least one source was published within the 18-month window.

Assessed at this edition's evidence cutoff: 2026-09-15. 18-month boundary: 2025-03-15.

Publication age does not tell us whether a claim is still valid. Reading an old source again does not make its publication date newer. An update date does not establish that the passage we used was updated.

Open in the glossary Reading notes · Structured record

In plain language

Generated intermediate steps before an answer, which can improve some task results but can also contain mistakes. [1] [2]

Reference this explanation or suggest a correction

Link to this explanation · Suggest a correction · How corrections work

Limits & distinctions

An explanation can be useful without faithfully reporting every influence on the answer. The label names generated text, not evidence of a human-like inner thought process. [3] [2]

Reference this explanation or suggest a correction

Link to this explanation · Suggest a correction · How corrections work

A fuller explanation

Chain-of-thought prompting supplies examples with intermediate steps so a model produces a similar sequence. The original paper reported gains on selected tasks. Later reasoning systems can also be trained to generate extended intermediate text. [1] [2]

Reference this explanation or suggest a correction

Link to this explanation · Suggest a correction · How corrections work

How it relates to the map

Atlas reading question: does a displayed explanation help check the answer, and what does it leave unverified? [2]

Reference this explanation or suggest a correction

Link to this explanation · Suggest a correction · How corrections work

Share this page

https://theaiatlas.org/ideas/chain-of-thought/

Download a share image · Vector image

Image previews are summaries. Keep the page link so readers can check the evidence.

Sources and what we read

  1. 1. Chain-of-Thought Prompting Elicits Reasoning in Large Language Models

    Source is over 18 months old.

    Publication dates and source age

    Sources counted: 1

    Newest dated source: 2022-01-28

    Assessed at this edition's evidence cutoff: 2026-09-15. 18-month boundary: 2025-03-15.

    Publication age does not tell us whether a claim is still valid. Reading an old source again does not make its publication date newer. An update date does not establish that the passage we used was updated.

    Read the abstract and version history. The paper reports improvements on selected arithmetic, commonsense and symbolic tasks with intermediate-step examples. It does not establish that generated explanations faithfully reveal internal computation.

  2. 2. Reasoning models don’t always say what they think

    Publication dates and source age

    Sources counted: 1

    Newest dated source: 2025-04-03

    At least one source was published within the 18-month window.

    Assessed at this edition's evidence cutoff: 2026-09-15. 18-month boundary: 2025-03-15.

    Publication age does not tell us whether a claim is still valid. Reading an old source again does not make its publication date newer. An update date does not establish that the passage we used was updated.

    Read methods, findings and limitations. Hint experiments used Claude 3.7 Sonnet and DeepSeek R1 on multiple-choice questions. Results do not cover every model, task or reasoning trace.

  3. 3. Language Models Don't Always Say What They Think: Unfaithful Explanations in Chain-of-Thought Prompting

    Source is over 18 months old.

    Publication dates and source age

    Sources counted: 1

    Newest dated source: 2023-05-07

    Assessed at this edition's evidence cutoff: 2026-09-15. 18-month boundary: 2025-03-15.

    Publication age does not tell us whether a claim is still valid. Reading an old source again does not make its publication date newer. An update date does not establish that the passage we used was updated.

    Read the abstract and version history. The experiments introduced biasing input features and examined generated explanations in GPT-3.5 and Claude 1.0. Their results are not a verdict on every model or every explanation.

Edition and machine-readable evidence

Content version 0.20.0. Evidence cutoff 2026-09-15; this does not mean every source was read on that day.

Pinned complete dataset · Complete evidence page · Agent consumption guide