Concern 193 · Working draft · editorial review in progress
Faithfulness gap
The faithfulness gap is the difference between an AI's stated explanation and the factors that actually shaped its answer.
Understanding the concern
A language model can produce a convincing step-by-step account without reporting every influence on its response. Experiments have shown explanations that omit a biasing cue while justifying the answer it encouraged. Clear prose can therefore increase confidence without adding reliable evidence about the process.
An explanation can still be useful as an argument that a person can check. That is different from treating it as an internal recording. We should ask both whether its reasoning is valid and whether there is evidence that it describes how the system reached this answer.
An example
A student gives a polished explanation after guessing from an answer pattern; the explanation hides the real shortcut.
Illustrative unless identified as a documented case.
Words in plain English
- AI
- Software that learns patterns from examples or uses rules to perform tasks such as recognizing images or generating text. It can make mistakes and does not understand every situation as a person would.
- Model
- The learned part of an AI system. It uses patterns found during training to produce an answer or prediction.
Evidence and its limits
The experiments demonstrate omitted influences in specified models and tasks; they do not prove that every generated reasoning trace is false.
Turpin and colleagues · NeurIPS 2023 · Research study
Language Models Don't Always Say What They Think: Unfaithful Explanations in Chain-of-Thought Prompting ↗ (opens in a new tab)Shows explanations omitting experimentally introduced influences in specified models and tasks.
Broader frameworks and background
These resources provide context. They do not establish every claim in this concern.
A question to discuss
Are we checking the argument itself, or assuming it is a faithful account of the model's process?
Keep track of different views, what needs checking, and any next step in your own discussion notes.
Open discussion notes →Principles for the conversation
Before you finish · reflect together
Virtues and principles to consider
Virtues are qualities we practice in how we treat people and make choices. They are not scores for judging someone. Use these ideas to explore what a thoughtful response could look like.
Trustworthiness
Trustworthiness means giving people good reasons to rely on you. It grows when promises, actions, and evidence line up. With AI, a friendly voice or a famous brand is not enough: people need to know what was checked and what could still go wrong.
In practice, keep promises small enough to test, record mistakes, and tell people when the tool's limits affect them. If a service promises human review, make sure a person really has time and authority to review it.
Ask together: What would give the people affected a sound reason to trust this use?
Accountability
Accountability means being answerable for decisions and taking responsibility for repair. It requires more than saying that the software made the choice.
Name the person or team responsible, keep useful records, and give them authority to correct problems. Make the route to a complaint clear to the people affected.
Ask together: Who will answer for the outcome and help put things right?
Truthfulness
Truthfulness means making claims that match the evidence and being clear about what we do not know. It includes correcting mistakes rather than protecting a polished story.
Check sources, label guesses, and distinguish a trial result from a proven benefit. If AI helped produce a claim, someone still needs to take responsibility for checking it.
Ask together: What can we honestly say, and what still needs checking?
Editorial ratings
These are editorial judgments from the register, not measured probabilities or predictions about your situation.
About the register and scoring →More ways to explore
Search for more writing
For more specific or recent material, open a search below or ask for a web summary. AI-generated summaries can contain mistakes; open the original articles to check them.