Skip to main content

Nudging through Friction: an Approach for Calibrating Trust in Explainable AI.

Naiseh, M, Al-Mansoori, R. S., Al-Thani, D., Jiang, N. and Ali, R., 2021. Nudging through Friction: an Approach for Calibrating Trust in Explainable AI. In: Proceedings of 2021 8th IEEE International Conference on Behavioural and Social Computing (BESC). New York: IEEE.

Full text available as:

[img] PDF
BESC 2021 - camera ready version.pdf - Accepted Version
Restricted to Repository staff only until 17 December 2023.
Available under License Creative Commons Attribution Non-commercial.

365kB

DOI: 10.1109/BESC53957.2021.9635271

Abstract

Explainability has become an essential requirement for safe and effective collaborative Human-AI environments, especially when generating recommendations through black-box modality. One goal of eXplainable AI (XAI) is to help humans calibrate their trust while working with intelligent systems, i.e., avoid situations where human decision-makers over-trust the AI when it is incorrect, or under-trust the AI when it is correct. XAI, in this context, aims to help humans understand AI reasoning and decide whether to follow or reject its recommendations. However, recent studies showed that users, on average, continue to overtrust (or under-trust) AI recommendations which is an indication of XAI's failure to support trust calibration. Such a failure to aid trust calibration was due to the assumption that XAI users would cognitively engage with explanations and interpret them without bias. In this work, we hypothesize that XAI interaction design can play a role in helping users' cognitive engagement with XAI and consequently enhance trust calibration. To this end, we propose friction as a Nudge-based approach to help XAI users to calibrate their trust in AI and present the results of a preliminary study of its potential in fulfilling that role.

Item Type:Book Section
ISBN:9781665400237
Additional Information:“© 2021 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.”
Uncontrolled Keywords:Social computing; Friction; Collaboration; Cognition; Calibration; Artificial intelligence; Intelligent systems; calibration; cognitive systems; decision making; explanation; human computer interaction; inference mechanisms; explainable AI; recommendation generation; black-box modality; human decision-makers; AI reasoning; trust calibration; XAI interaction design; collaborative human-AI environments; intelligent systems; AI recommendation undertrust; AI recommendation overtrust; XAI failure; user cognitive engagement; nudge-based approach; Human-AI Interaction; Explainable AI; Digital Nudging; Friction; Calibrated Trust
Group:Faculty of Science & Technology
ID Code:38675
Deposited By: Symplectic RT2
Deposited On:04 Aug 2023 11:52
Last Modified:04 Aug 2023 12:05

Downloads

Downloads per month over past year

More statistics for this item...
Repository Staff Only -