A field guide to AI positions

Post-training

Sources are over 18 months old.

Publication dates and source age

Sources counted: 2

Newest dated source: 2024-07-31

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

Further training after pretraining, intended to adapt a model’s abilities and behavior. [1]

Reference this explanation or suggest a correction

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

Limits & distinctions

Post-training names a development stage, not a safety certificate. Improvements on selected tasks leave other failures possible. [1]

Reference this explanation or suggest a correction

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

A fuller explanation

Developers can train on demonstrations, preferred answers or rewards. These methods may target instruction following, coding or responses to harmful requests. Different developers use different combinations. [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

Inspect the training goal, whose feedback was used and which results were tested. [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/post-training/

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. The Llama 3 Herd of Models

    Source is over 18 months old.

    Publication dates and source age

    Sources counted: 1

    Newest dated source: 2024-07-31

    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 two training stages, post-training methods and section 5.4.8 limitations in version 2. Dates follow arXiv submission history. One documented approach, not a universal training recipe.

  2. 2. Training language models to follow instructions with human feedback

    Source is over 18 months old.

    Publication dates and source age

    Sources counted: 1

    Newest dated source: 2022-03-04

    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 abstract, section 3.1's demonstrations/comparisons/reward-model procedure and section 5.3's limitations. Human preference judgments and improved results on the authors' tasks do not establish universal alignment or safety. Publication date checked on the arXiv abstract page.

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