A field guide to AI positions

In-context learning

Model behavior.

Dated sources are over 18 months old; other dates are unknown.

Publication dates and source age

Sources counted: 3

Newest dated source: 2022-09-24

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

Some publication dates are unknown; the newest dated source may not be the newest source overall.

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

Prepared with AI assistance. Not independently fact-checked. Original sources and qualifications are below.

In plain language

Using material in the current prompt to adapt an answer, without a new training run. [1] [2]

Reference this explanation or suggest a correction

Explanation based on the linked sources. Claim ID: claim-term-in-context-learning-1a5192ba3d7825ca26b24a72. Edition 0.20.0.

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

Limits & distinctions

This is not a claim that a conversation permanently teaches the underlying model. Accounts of the internal mechanism remain dependent on the model and evidence studied. [3] [2]

Reference this explanation or suggest a correction

Explanation based on the linked sources. Claim ID: claim-term-in-context-learning-09422ce4d5c74cb753a9bb98. Edition 0.20.0.

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

A fuller explanation

A prompt can provide examples or a pattern that guides the next response. This makes some task adaptation possible without a new training run. Researchers also study how this behavior arises inside transformers. [1] [2]

Reference this explanation or suggest a correction

Explanation based on the linked sources. Claim ID: claim-term-in-context-learning-1e4c26398ee834b2e16dc7b8. Edition 0.20.0.

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

How it relates to the map

Atlas reading question: did a demonstration change the model itself, or only the information in its input? [1] [2]

Reference this explanation or suggest a correction

Editorial interpretation or qualification. Claim ID: claim-term-in-context-learning-25f52a21ad9f2e54a62ed1b2. Edition 0.20.0.

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

Share this page

https://theaiatlas.org/ideas/in-context-learning/

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. LLMs: Fine-tuning, distillation, and prompt engineering

    Google for Developers · First-hand source · Published date unavailable · Updated 2025-12-03 · Material last read 2026-09-15

    Publication dates and source age

    Sources counted: 1

    Publication dates are unavailable.

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

    Some publication dates are unknown; the newest dated source may not be the newest source overall.

    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 scope is described in the source note.

    No archive check recorded.

    Read fine-tuning and prompt engineering, including the distinction between parameter updates and examples supplied as input. Used to distinguish these processes, without adopting general claims that fine-tuning is always necessary or improves every task.

    Source ID: google-llm-tuning

  2. 2. In-context Learning and Induction Heads

    Catherine Olsson and coauthors / arXiv · First-hand source · Published 2022-09-24 · Material last read 2026-09-15

    Source is over 18 months old.

    Publication dates and source age

    Sources counted: 1

    Newest dated source: 2022-09-24

    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 scope is described in the source note.

    No archive check recorded.

    Read the abstract and submission record. The authors report causal evidence in small attention-only models and indirect or correlational evidence for their wider mechanism hypothesis. The glossary does not present that hypothesis as settled for all models.

    Source ID: glossary-eval-induction

  3. 3. Language Models are Few-Shot Learners

    Tom B. Brown and coauthors / arXiv · First-hand source · Published 2020-05-28 · Updated 2020-07-22 · Material last read 2026-09-15

    Source is over 18 months old.

    Publication dates and source age

    Sources counted: 1

    Newest dated source: 2020-05-28

    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 scope is described in the source note.

    No archive check recorded.

    Read the abstract, section 2 on zero-shot and few-shot settings, and section 4 on training-data overlap. Version 4 is dated 22 July 2020. The reported results concern GPT-3 and are not current model rankings; detected overlap did not uniformly inflate scores.

    Source ID: glossary-eval-gpt3

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