Protocol
Test the confidence cue, including the words
Replacing an unreliable percentage with “probably” does not finish the job. Check both what the cue means and how people use it.
Before you use it
- Use when
- A product plans to show users a confidence percentage because it seems transparent.
Keep this limit in mind
- Even calibrated confidence cannot replace source evidence or authorization for high-stakes decisions.
Current editorial reading
Check the signal and the display
For a percentage, compare predicted probabilities with observed results on relevant cases. For verbal labels, check whether higher confidence actually marks more reliable answers. Then compare decisions with and without the proposed display, including wrong answers accepted and correct answers rejected. A document checker that hides its percentage but adds “high confidence” still needs this test.
Keep the evidence in scope
The cited logic-puzzle experiment used high, medium and low labels, not numerical probabilities. Another experiment found improved accuracy with first-person uncertainty wording; general-perspective wording had weaker, statistically inconclusive effects. Neither validates a new product’s display. Treat wording, failure-mode information and withholding the cue as options to evaluate; do not assume one is a safe substitute.
Take it with you
Keep the display tied to the model, task and version tested. If the signal is unreliable or the display worsens decisions, revise or withhold it. Confidence never supplies missing evidence or permission to act.
Sources and evidence (2)
What we checked
The AAAI experiment varied categorical confidence with advice correctness in a logic-puzzle task; the results motivate testing reliance behavior.
Selected passages, not a full-paper appraisal. The proposed product test is an editorial application.
Too Sure for Our Own Good: A User Study on AI Confidence and Human Reliance · Methods and Results, printed pp. 17446–17449
That experiment did not test displayed numerical probabilities, and the authors identify limits to transfer beyond the puzzle task.
Categorical confidence and numerical probability calibration must not be treated as the same tested intervention.
Too Sure for Our Own Good: A User Study on AI Confidence and Human Reliance · Limitations and Future Work, printed p. 17451
The FAccT abstract reports improved accuracy with first-person wording; exploratory analysis suggests reduced overreliance. General-perspective effects were weaker and nonsignificant.
Abstract-only appraisal. The simulated medical-question task does not establish clinical effectiveness or validate arbitrary hedging language.
“I’m Not Sure, But…”: Examining the Impact of Large Language Models’ Uncertainty Expression on User Reliance and Trust · Abstract; arXiv:2405.00623v2
Editorial sources (2)
Save and practise this idea
My learning
Read. Recall. Repeat.
Save this idea and return to it on any device.
Keep exploring
Try it in a task guide
These guides use this edition of the method alongside other ideas for the same task.
Keep model confidence separate from evidence.Verify an AI Output Before You Act
Connected ideas
You are readingTest the confidence cue, including the words
Ideas that link here
These ideas link to this one. Check their conditions and limits before use.
Use before this ideaJudge AI confidence by whether it separates right from wrong
Original edition evidence and sources
These records belong to the original released edition. The current editorial reading has its own evidence above; neither set silently replaces the other.
An AAAI 2026 experiment found well-calibrated AI confidence improved participant decision accuracy more than miscalibrated confidence, while miscalibrated cues increased reliance-related errors.
The task involved logic puzzles and controlled confidence manipulations.
Too Sure for Our Own Good: A User Study on AI Confidence and Human Reliance · Results
A 2026 experiment found visual uncertainty cues could increase users' subjective confidence-accuracy discrimination while simultaneously increasing behavioral overreliance on incorrect LLM outputs.
Interface effects depend on cue design and task; more uncertainty display is not automatically harmful.
Original edition, downloads and provenance
The reading above is editorial version 1.0.0, bound to this exact source edition. The original data and saved downloads retain that edition and the separate editorial layer. They may contain earlier wording; use the current reading above when interpreting it.
Version 0.1.0
No review details are supplied for this edition.
Read the original edition and overlay as JSON · Release details