Trust and Reliance in XAI -- Distinguishing Between Attitudinal and Behavioral Measures

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Scharowski, Nicolas, Perrig, Sebastian A. C., von Felten, Nick, Brühlmann, Florian
Format: Preprint
Published: 2022
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910939208482816
author Scharowski, Nicolas
Perrig, Sebastian A. C.
von Felten, Nick
Brühlmann, Florian
author_facet Scharowski, Nicolas
Perrig, Sebastian A. C.
von Felten, Nick
Brühlmann, Florian
contents Trust is often cited as an essential criterion for the effective use and real-world deployment of AI. Researchers argue that AI should be more transparent to increase trust, making transparency one of the main goals of XAI. Nevertheless, empirical research on this topic is inconclusive regarding the effect of transparency on trust. An explanation for this ambiguity could be that trust is operationalized differently within XAI. In this position paper, we advocate for a clear distinction between behavioral (objective) measures of reliance and attitudinal (subjective) measures of trust. However, researchers sometimes appear to use behavioral measures when intending to capture trust, although attitudinal measures would be more appropriate. Based on past research, we emphasize that there are sound theoretical reasons to keep trust and reliance separate. Properly distinguishing these two concepts provides a more comprehensive understanding of how transparency affects trust and reliance, benefiting future XAI research.
format Preprint
id arxiv_https___arxiv_org_abs_2203_12318
institution arXiv
publishDate 2022
record_format arxiv
spellingShingle Trust and Reliance in XAI -- Distinguishing Between Attitudinal and Behavioral Measures
Scharowski, Nicolas
Perrig, Sebastian A. C.
von Felten, Nick
Brühlmann, Florian
Human-Computer Interaction
Artificial Intelligence
H.5.0; I.2.0
Trust is often cited as an essential criterion for the effective use and real-world deployment of AI. Researchers argue that AI should be more transparent to increase trust, making transparency one of the main goals of XAI. Nevertheless, empirical research on this topic is inconclusive regarding the effect of transparency on trust. An explanation for this ambiguity could be that trust is operationalized differently within XAI. In this position paper, we advocate for a clear distinction between behavioral (objective) measures of reliance and attitudinal (subjective) measures of trust. However, researchers sometimes appear to use behavioral measures when intending to capture trust, although attitudinal measures would be more appropriate. Based on past research, we emphasize that there are sound theoretical reasons to keep trust and reliance separate. Properly distinguishing these two concepts provides a more comprehensive understanding of how transparency affects trust and reliance, benefiting future XAI research.
title Trust and Reliance in XAI -- Distinguishing Between Attitudinal and Behavioral Measures
topic Human-Computer Interaction
Artificial Intelligence
H.5.0; I.2.0
url https://arxiv.org/abs/2203.12318