Effects of Presenting Multiple Types of AI Explanations for Visual Task
Open Access
- 24 November 2024
- conference paper
- Published by Association for Computing Machinery (ACM)
- p. 160-166
Abstract
Explainable AI (XAI) has been developed to make AI understandable to humans by providing explanations of its outputs. However, multiple types of AI explanations displayed on a screen could distort users’ trust in AI and their decision to rely on it. This could lead to poor task performance. In this study, we experimentally investigated the influence of AI explanations on trust and acceptance of AI results using a visual task. As a result, we found that participants increased their trust and acceptance of AI results with multiple types of explanations even though this did not improve task performance. These results, showing over-trust and over-reliance in human-agent interaction, were discussed along with cognitive load and cognitive bias caused by XAI.Keywords
Funding Information
- Japan Science and Technology Agency (JPMJCR21D4)
This publication has 29 references indexed in Scilit:
- How does the model make predictions? A systematic literature review on the explainability power of machine learning in healthcareArtificial Intelligence in Medicine, 2023
- How the different explanation classes impact trust calibration: The case of clinical decision support systemsInternational Journal of Human-Computer Studies, 2022
- An extensive dataset for successful recognition of fresh and rotten fruitsData in Brief, 2022
- Introduction of human-centric AI assistant to aid radiologists for multimodal breast image classificationInternational Journal of Human-Computer Studies, 2021
- Empirical Evaluations of Framework for Adaptive Trust Calibration in Human-AI CooperationIEEE Access, 2020
- A Situation Awareness-Based Framework for Design and Evaluation of Explainable AI2020
- Towards a Theory of Longitudinal Trust Calibration in Human–Robot TeamsInternational Journal of Social Robotics, 2019
- Grad-CAM: Visual Explanations from Deep Networks via Gradient-Based Localization2017
- Automated diagnostic aids: The effects of aid reliability on users' trust and relianceTheoretical Issues in Ergonomics Science, 2001
- Trust, control strategies and allocation of function in human-machine systemsErgonomics, 1992