Towards a Novel Measure of User Trust in XAI Systems

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Miró-Nicolau, Miquel, Moyà-Alcover, Gabriel, Jaume-i-Capó, Antoni, González-Hidalgo, Manuel, Ghazel, Adel, Campello, Maria Gemma Sempere, Sancho, Juan Antonio Palmer
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909675024285696
author Miró-Nicolau, Miquel
Moyà-Alcover, Gabriel
Jaume-i-Capó, Antoni
González-Hidalgo, Manuel
Ghazel, Adel
Campello, Maria Gemma Sempere
Sancho, Juan Antonio Palmer
author_facet Miró-Nicolau, Miquel
Moyà-Alcover, Gabriel
Jaume-i-Capó, Antoni
González-Hidalgo, Manuel
Ghazel, Adel
Campello, Maria Gemma Sempere
Sancho, Juan Antonio Palmer
contents 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 trust measure 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 three case studies showing an improvement respect the state-of-the-art, with an increased sensitiviy to different scenarios.
format Preprint
id arxiv_https___arxiv_org_abs_2405_05766
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Towards a Novel Measure of User Trust in XAI Systems
Miró-Nicolau, Miquel
Moyà-Alcover, Gabriel
Jaume-i-Capó, Antoni
González-Hidalgo, Manuel
Ghazel, Adel
Campello, Maria Gemma Sempere
Sancho, Juan Antonio Palmer
Computer Vision and Pattern Recognition
Artificial Intelligence
Machine Learning
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 trust measure 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 three case studies showing an improvement respect the state-of-the-art, with an increased sensitiviy to different scenarios.
title Towards a Novel Measure of User Trust in XAI Systems
topic Computer Vision and Pattern Recognition
Artificial Intelligence
Machine Learning
url https://arxiv.org/abs/2405.05766