AI · Controlled decision experiment.

Effect of confidence and explanation on accuracy and trust calibration

FAT*. · 2020

Zhang, Y., Liao, Q. V., Bellamy, R. K. E.

Original paper ↗

Summary

Confidence displays and explanations affect accuracy and trust calibration; explanation alone is insufficient.

For your marketing

Possible founder application

Expose calibrated confidence and test appropriate acceptance/rejection.

Reported result

What the study found

Confidence displays and explanations affect accuracy and trust calibration; explanation alone is insufficient.

Research question

What the authors investigated

How do confidence and explanation calibrate AI reliance?

Design

Controlled decision experiment.

Sample and setting

Participants making classification decisions with AI confidence/explanations.

Scope and transfer

Limitations to keep in view

Laboratory classification task.

Research sources

Publisher abstract/full text supports the reported design, sample, and findings.

Additional research source ↗

Study strength

4/5 Research record provides a clear design and context; apply the finding within its stated limits.

How this was assessed

The 1–5 evidence-check score is a practical reading aid, not a formal peer review or a probability that a conclusion is true. It combines design strength (2 points), sample reporting (1), comparison/control clarity (1), and how much of the paper could be checked (1). Access affects how confidently this directory can assess a study, not the study's underlying quality. Blinding is reported separately because it is not relevant to every design.

Design transparency · 2/2

Based on the reported study design in the retrieved source.

Sample and setting · 1/1

The sample context is stated; a numerical count is preserved only when reported.

Outcome clarity · 1/1

The finding is summarized from publisher or article metadata.

Access for checking · 1/1

Full text was identified.

Double-blind? The retrieved publisher record does not establish whether participants or outcome assessors were blinded.

Read the paper