Back to Publications
conference · 2025

Human-in-the-Loop Interfaces for Trustworthy AI Decision Support

Abhiraj Bibhar, Riya Patel · ACM CHI Conference on Human Factors in Computing Systems

HCITrustworthy AI

Abstract

We report on a mixed-methods study of 48 clinicians interacting with three AI-assisted diagnostic interfaces that varied in how they presented model confidence and supporting evidence. Confidence calibration displays significantly improved appropriate reliance on model suggestions, and clinicians consistently preferred interfaces that surfaced underlying evidence rather than raw confidence scores. Time pressure substantially altered how much clinicians engaged with explanatory content — a factor largely absent from prior lab-based evaluations of AI decision support.

Key contributions

  • A controlled comparison of three confidence-communication strategies in a clinical decision-support setting.
  • Evidence that time pressure changes reliance behavior in ways lab studies typically miss.
  • Design guidelines for interfaces that support — rather than override — clinical judgment.

Honorable Mention Award, ACM CHI 2026 (top 5% of submissions).

PDF DOI Publisher
Back to all publications

On this page

Authors

  • A Abhiraj Bibhar (this author)
  • R Riya Patel

Cite this paper

Bibhar, A. & Patel, R. (2025). Human-in-the-Loop Interfaces for Trustworthy AI Decision Support. ACM CHI Conference on Human Factors in Computing Systems.

@inproceedings{bibhar2025human,
  title     = {Human-in-the-Loop Interfaces for Trustworthy AI Decision Support},
  author    = {Bibhar, Abhiraj and Patel, Riya},
  booktitle   = {ACM CHI Conference on Human Factors in Computing Systems},
  year      = {2025}
}