BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:From Explanation to Trust: Modeling and Measuring Trust in Explain
 able Decision Support - Mohsen Abbaspour\, Eindhoven University of Technol
 ogy
DTSTART:20251016T150000Z
DTEND:20251016T154500Z
UID:TALK234808@talks.cam.ac.uk
CONTACT:Pietro Lio
DESCRIPTION:This seminar presents my findings from doctoral research condu
 cted at Eindhoven University of Technology\, together with research carrie
 d out as a guest at the Computer Laboratory of the University of Cambridge
 \, on human trust in AI-based decision support. The thesis investigates tr
 ust in machine learning models through three complementary studies.\n\nHig
 hlights include a case study on COVID-19 diagnosis\, where perceived trust
  of medical experts—understood as self-reported trust—was modeled as a
  complex\, context-dependent phenomenon rather than a single dimension. In
  the next case study on distal myopathy\, interpretability quality was ass
 essed both through radiologists’ evaluations and through objective metri
 cs from the XAI literature. A broader human-subjects study further reveale
 d a clear distinction between perceived trust and demonstrated trust\, the
  latter referring to the actual delegation of decisions to AI by human use
 rs.\n\nAcross these studies\, a notable gap was identified between objecti
 ve metrics of explainability and expert assessments\, underscoring the dif
 ficulty of aligning computational measures with professional judgment. Tog
 ether\, these findings highlight discrepancies between reported attitudes\
 , expert opinion\, and actual behavior\, offering concrete guidance for th
 e design of AI-based decision support that are both interpretable and trus
 tworthy.
LOCATION:Computer Laboratory\, William Gates Building\, Room FW11
END:VEVENT
END:VCALENDAR