Evaluating the Influences of Explanation Style on Human-AI Reliance

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Casolin, Emma, Salim, Flora D., Newell, Ben
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866929561239814144
author Casolin, Emma
Salim, Flora D.
Newell, Ben
author_facet Casolin, Emma
Salim, Flora D.
Newell, Ben
contents Explainable AI (XAI) aims to support appropriate human-AI reliance by increasing the interpretability of complex model decisions. Despite the proliferation of proposed methods, there is mixed evidence surrounding the effects of different styles of XAI explanations on human-AI reliance. Interpreting these conflicting findings requires an understanding of the individual and combined qualities of different explanation styles that influence appropriate and inappropriate human-AI reliance, and the role of interpretability in this interaction. In this study, we investigate the influences of feature-based, example-based, and combined feature- and example-based XAI methods on human-AI reliance through a two-part experimental study with 274 participants comparing these explanation style conditions. Our findings suggest differences between feature-based and example-based explanation styles beyond interpretability that affect human-AI reliance patterns across differences in individual performance and task complexity. Our work highlights the importance of adapting explanations to their specific users and context over maximising broad interpretability.
format Preprint
id arxiv_https___arxiv_org_abs_2410_20067
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Evaluating the Influences of Explanation Style on Human-AI Reliance
Casolin, Emma
Salim, Flora D.
Newell, Ben
Human-Computer Interaction
Explainable AI (XAI) aims to support appropriate human-AI reliance by increasing the interpretability of complex model decisions. Despite the proliferation of proposed methods, there is mixed evidence surrounding the effects of different styles of XAI explanations on human-AI reliance. Interpreting these conflicting findings requires an understanding of the individual and combined qualities of different explanation styles that influence appropriate and inappropriate human-AI reliance, and the role of interpretability in this interaction. In this study, we investigate the influences of feature-based, example-based, and combined feature- and example-based XAI methods on human-AI reliance through a two-part experimental study with 274 participants comparing these explanation style conditions. Our findings suggest differences between feature-based and example-based explanation styles beyond interpretability that affect human-AI reliance patterns across differences in individual performance and task complexity. Our work highlights the importance of adapting explanations to their specific users and context over maximising broad interpretability.
title Evaluating the Influences of Explanation Style on Human-AI Reliance
topic Human-Computer Interaction
url https://arxiv.org/abs/2410.20067