Investigating the Role of Explainability and AI Literacy in User Compliance

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Kühl, Niklas, Meske, Christian, Nitsche, Maximilian, Lobana, Jodie
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916293266898944
author Kühl, Niklas
Meske, Christian
Nitsche, Maximilian
Lobana, Jodie
author_facet Kühl, Niklas
Meske, Christian
Nitsche, Maximilian
Lobana, Jodie
contents AI is becoming increasingly common across different domains. However, as sophisticated AI-based systems are often black-boxed, rendering the decision-making logic opaque, users find it challenging to comply with their recommendations. Although researchers are investigating Explainable AI (XAI) to increase the transparency of the underlying machine learning models, it is unclear what types of explanations are effective and what other factors increase compliance. To better understand the interplay of these factors, we conducted an experiment with 562 participants who were presented with the recommendations of an AI and two different types of XAI. We find that users' compliance increases with the introduction of XAI but is also affected by AI literacy. We also find that the relationships between AI literacy XAI and users' compliance are mediated by the users' mental model of AI. Our study has several implications for successfully designing AI-based systems utilizing XAI.
format Preprint
id arxiv_https___arxiv_org_abs_2406_12660
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Investigating the Role of Explainability and AI Literacy in User Compliance
Kühl, Niklas
Meske, Christian
Nitsche, Maximilian
Lobana, Jodie
Artificial Intelligence
AI is becoming increasingly common across different domains. However, as sophisticated AI-based systems are often black-boxed, rendering the decision-making logic opaque, users find it challenging to comply with their recommendations. Although researchers are investigating Explainable AI (XAI) to increase the transparency of the underlying machine learning models, it is unclear what types of explanations are effective and what other factors increase compliance. To better understand the interplay of these factors, we conducted an experiment with 562 participants who were presented with the recommendations of an AI and two different types of XAI. We find that users' compliance increases with the introduction of XAI but is also affected by AI literacy. We also find that the relationships between AI literacy XAI and users' compliance are mediated by the users' mental model of AI. Our study has several implications for successfully designing AI-based systems utilizing XAI.
title Investigating the Role of Explainability and AI Literacy in User Compliance
topic Artificial Intelligence
url https://arxiv.org/abs/2406.12660