Explanation faithfulness
Publication dates and source age
Sources counted: 2
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
Whether an explanation accurately reflects what influenced an answer, rather than merely sounding plausible. [1] [2]
Reference this explanation or suggest a correction
Link to this explanation · Suggest a correction · How corrections work
Limits & distinctions
A correct answer can have an incomplete explanation. The cited hint experiments found omissions in particular models and tasks; they do not show that every reasoning trace is useless. [1] [2]
Reference this explanation or suggest a correction
Link to this explanation · Suggest a correction · How corrections work
A fuller explanation
Researchers can introduce a hint, observe whether it changes an answer, and check whether the explanation mentions it. Such tests examine a particular causal influence, not every step of the underlying computation. [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: what evidence connects an explanation to the process that produced the answer? [1] [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/explanation-faithfulness/
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. 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.
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.
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