A field guide to AI positions

Model distillation

Inside a model.

Source is over 18 months old.

Publication dates and source age

Sources counted: 1

Newest dated source: 2015-03-09

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

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

In plain language

Training a model to match outputs from another model, often to make it cheaper to run. [1]

Reference this explanation or suggest a correction

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

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

Limits & distinctions

The smaller model may not match every output or capability. Distillation does not guarantee identical performance. [1]

Reference this explanation or suggest a correction

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

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

A fuller explanation

In the cited method, a larger model supplies probabilities as training targets for a smaller one. The target is output behavior, rather than copying the original model’s weights. [1]

Reference this explanation or suggest a correction

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

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

How it relates to the map

Ask which tasks the smaller model was tested on and how its results changed. [1]

Reference this explanation or suggest a correction

Editorial interpretation or qualification. Claim ID: claim-term-distillation-25f52a21ad9f2e54a62ed1b2. Edition 0.20.0.

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

Share this page

https://theaiatlas.org/ideas/distillation/

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. Distilling the Knowledge in a Neural Network

    Geoffrey Hinton, Oriol Vinyals and Jeff Dean / arXiv · First-hand source · Published 2015-03-09 · Material last read 2026-09-15

    Source is over 18 months old.

    Publication dates and source age

    Sources counted: 1

    Newest dated source: 2015-03-09

    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 introduction and distillation method, including probability targets and imperfect matching. Date checked on arXiv. The historical experiments do not establish performance for current distilled models.

    Source ID: glossary-model-distillation

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