ScholarMate
English简体中文繁體中文
客服热线:400-1616-289
登录注册
期刊论文

Evaluating XAI: A comparison of rule-based and example-based explanations

van der Waa, Jasper*; Nieuwburg, Elisabeth; Cremers, Anita; Neerincx, Mark
Artificial Intelligence2021-2DOI: 10.1016/j.artint.2020.103404
170被引20阅读
引用收藏
分享

摘要

Current developments in Artificial Intelligence (AI) led to a resurgence of Explainable AI (XAI). New methods are being researched to obtain information from AI systems in order to generate explanations for their output. However, there is an overall lack of valid and reliable evaluations of the effects on users' experience of, and behavior in response to explanations. New XAI methods are often based on an intuitive notion what an effective explanation should be. Ruleand example-based contrastive explanations are two exemplary explanation styles. In this study we evaluate the effects of these two explanation styles on system understanding, persuasive power and task performance in the context of decision support in diabetes self-management. Furthermore, we provide three sets of recommendations based on our experience designing this evaluation to help improve future evaluations. Our results show that rule-based explanations have a small positive effect on system understanding, whereas both ruleand example-based explanations seem to persuade users in following the advice even when incorrect. Neither explanation improves task performance compared to no explanation. This can be explained by the fact that both explanation styles only provide details relevant for a single decision, not the underlying rational or causality. These results show the importance of user evaluations in assessing the current assumptions and intuitions on effective explanations.

学科与关键词

关键词
Explainable Artificial Intelligence (XAI)User evaluationsContrastive explanationsArtificial Intelligence (AI)Machine learningDecision support systems
相关
加载中…
  • Towards Human-Centered Explainable AI: A Survey of User Studies for Model Explanations
    Rong, Yao*; Leemann, Tobias; Nguyen, Thai-Trang; Fiedler, Lisa; Qian, Peizhu; Unhelkar, Vaibhav; Seidel, Tina; Kasneci, Gjergji; Kasneci, EnkelejdaIEEE Transactions on Pattern Analysis and Machine Intelligence, 2024, 46(4): 2104-2122.被引 27
  • Notions of explainability and evaluation approaches for explainable artificial intelligence
    Vilone, Giulia*; Longo, LucaInformation Fusion, 2021, 76: 89-106.被引 237
  • Who needs explanation and when? Juggling explainable AI and user epistemic uncertainty
    Jiang, Jinglu; Kahai, Surinder; Yang, Ming*International Journal of Human Computer Studies, 2022, 165: 102839.被引 26
查看全部 →

发表信息

论文状态
公开发表
期刊
Artificial Intelligence
发表日期
2021-02
卷期
第 291 卷
页码
103404
DOI
10.1016/j.artint.2020.103404
语言
ENGLISH
期刊收录
NSL
期刊等级
2区
成果收录
SCIE
资助标注
project ERP Explainable Artificial Intelligence from TNO [060.38608]; ERP FATE from TNO [060.43385]; Technical University of Delft; University of Amsterdam

作者

  • v

    van der Waa, Jasper (通讯) (第一作者)

  • N

    Nieuwburg, Elisabeth

查看全部 4 位作者收起作者
  • C

    Cremers, Anita

  • N

    Neerincx, Mark

登录解锁更多功能

  • 收藏这篇,随时在“我的 · 收藏”找回
  • 认领你的成果,生成推广素材
  • 关注作者获取最新成果
  • 加入项目组、协同写作
注册 / 登录

产品服务

  • 科研之友
  • 创新城
  • 科创云

服务支持

  • 帮助中心
  • 隐私政策
  • 服务条款

联系方式

在线客服:【】
客服热线:400-1616-289
电子邮箱:support@scholarmate.com

关注或下载科研之友

微信二维码
微信公众号
客户端下载二维码
下载客户端
科研成果科研人员科研机构科研动态爱瑞思软件

©2026 深圳市科研之友网络服务有限公司

公安备案图标粤公网安备 44030502000213
粤ICP备 16046710 号粤B2-20110417