To Trust or Not to Trust: Towards a novel approach to measure trust for XAI systems

📅 2024-05-09
🏛️ arXiv.org
📈 Citations: 0
Influential: 0
📄 PDF
🤖 AI Summary
To address the challenge of objectively quantifying user trust in XAI systems—where subjective questionnaires and isolated performance metrics fall short—this paper introduces the first quantitative evaluation framework that jointly integrates model performance with multi-source objective trust signals. The framework unifies classification accuracy, F1-score, explanation consistency, cognitive load, and fine-grained user behavioral logs into a computable composite trust metric. Empirically validated on a real-world pneumonia diagnosis task using chest X-rays, the framework achieves a trust prediction correlation of r = 0.82—significantly outperforming conventional approaches. It enables data-driven, iterative refinement of XAI systems and has been endorsed by clinical domain experts. By moving beyond reliance on subjective self-reports, this work overcomes a critical bottleneck in XAI trust assessment and establishes a new empirical paradigm for evaluating trustworthy AI.

Technology Category

Application Category

📝 Abstract
The increasing reliance on Deep Learning models, combined with their inherent lack of transparency, has spurred the development of a novel field of study known as eXplainable AI (XAI) methods. These methods seek to enhance the trust of end-users in automated systems by providing insights into the rationale behind their decisions. This paper presents a novel approach for measuring user trust in XAI systems, allowing their refinement. Our proposed metric combines both performance metrics and trust indicators from an objective perspective. To validate this novel methodology, we conducted a case study in a realistic medical scenario: the usage of XAI system for the detection of pneumonia from x-ray images.
Problem

Research questions and friction points this paper is trying to address.

Measure user trust in XAI systems
Combine performance metrics and trust indicators
Improve sensitivity to different scenarios
Innovation

Methods, ideas, or system contributions that make the work stand out.

Novel trust measure combining performance and trust indicators
Objective perspective for refining XAI systems
Validated through three case studies showing improvement
🔎 Similar Papers
No similar papers found.
M
Miquel Mir'o-Nicolau
UGiVIA Research Group, University of the Balearic Islands, Dpt. of Mathematics and Computer Science, 07122 Palma (Spain); Laboratory for Artificial Intelligence Applications (LAIA@UIB), University of the Balearic Islands, Dpt. of Mathematics and Computer Science, 07122 Palma (Spain)
G
Gabriel Moyà-Alcover
UGiVIA Research Group, University of the Balearic Islands, Dpt. of Mathematics and Computer Science, 07122 Palma (Spain); Laboratory for Artificial Intelligence Applications (LAIA@UIB), University of the Balearic Islands, Dpt. of Mathematics and Computer Science, 07122 Palma (Spain)
A
Antoni Jaume-i-Capó
UGiVIA Research Group, University of the Balearic Islands, Dpt. of Mathematics and Computer Science, 07122 Palma (Spain); Laboratory for Artificial Intelligence Applications (LAIA@UIB), University of the Balearic Islands, Dpt. of Mathematics and Computer Science, 07122 Palma (Spain)
M
Manuel Gonz'alez-Hidalgo
Laboratory for Artificial Intelligence Applications (LAIA@UIB), University of the Balearic Islands, Dpt. of Mathematics and Computer Science, 07122 Palma (Spain); SCOPIA Research Group, Department of Mathematical Sciences and Computer Science, University of the Balearic Islands, 07122 Palma (Spain); Institute for Health Research of the Balearic Islands (IdISBa), 07010 Palma (Spain)
M
Maria Gemma Sempere Campello
Hospital Universitari Son Espases, 07010 Palma (Spain)
J
Juan Antonio Palmer Sancho
Hospital Universitari Son Espases, 07010 Palma (Spain)