Towards human-centered explainable ai: A survey of user studies for model explanations

Y Rong, T Leemann, TT Nguyen… - IEEE transactions on …, 2023 - ieeexplore.ieee.org
Explainable AI (XAI) is widely viewed as a sine qua non for ever-expanding AI research. A
better understanding of the needs of XAI users, as well as human-centered evaluations of …

A Pilot Study on Clinician-AI Collaboration in Diagnosing Depression from Speech

K Feng, T Chaspari - arxiv preprint arxiv:2410.18297, 2024 - arxiv.org
This study investigates clinicians' perceptions and attitudes toward an assistive artificial
intelligence (AI) system that employs a speech-based explainable ML algorithm for detecting …

[HTML][HTML] An Overview of the Empirical Evaluation of Explainable AI (XAI): A Comprehensive Guideline for User-Centered Evaluation in XAI

S Naveed, G Stevens, D Robin-Kern - Applied Sciences, 2024 - mdpi.com
Recent advances in technology have propelled Artificial Intelligence (AI) into a crucial role in
everyday life, enhancing human performance through sophisticated models and algorithms …

Explainable ai-based humerus fracture detection and classification from x-ray images

K Barua, T Mahmud, A Barua… - … on Computer and …, 2023 - ieeexplore.ieee.org
The human skeletal framework relies heavily on bones, and one such crucial component is
the “Humerus.” Positioned in the upper arm, extending from the shoulder to the elbow …

Caution to the exemplars: On the intriguing effects of example choice on human trust in xai

T Leemann, Y Rong, TT Nguyen, E Kasneci… - XAI in Action: Past …, 2023 - openreview.net
In model audits explainable AI (XAI) systems are usually presented to human auditors on a
limited number of examples due to time constraints. However, recent literature has …

Introduction to Eye Tracking: A Hands-On Tutorial for Students and Practitioners

E Kasneci, H Gao, S Ozdel, V Maquiling… - arxiv preprint arxiv …, 2024 - arxiv.org
Eye-tracking technology is widely used in various application areas such as psychology,
neuroscience, marketing, and human-computer interaction, as it is a valuable tool for …

Social acceptance of artificial intelligence (AI) application for improving medical service diagnostics

J Ejdys, M Czerwińska, R Ginevičius - Human Technology, 2024 - ht.csr-pub.eu
The aim of the conducted research was to assess the attitude of the Polish society towards
the use of artificial intelligence in medical diagnostics. In the research process, we sought …

The Decoupling Concept Bottleneck Model

R Zhang, X Du, J Yan, S Zhang - IEEE Transactions on Pattern …, 2024 - ieeexplore.ieee.org
The Concept Bottleneck Model (CBM) is an interpretable neural network that leverages high-
level concepts to explain model decisions and conduct human-machine interaction …

Faithful Attention Explainer: Verbalizing Decisions Based on Discriminative Features

Y Rong, D Scheerer, E Kasneci - arxiv preprint arxiv:2405.13032, 2024 - arxiv.org
In recent years, model explanation methods have been designed to interpret model
decisions faithfully and intuitively so that users can easily understand them. In this paper, we …