The Impact of Imperfect XAI on Human-AI Decision-Making

作者
Katelyn Morrison,Philipp Spitzer,Violet Turri,Michelle Feng,Niklas Kühl,Adam Perer
出处
期刊: [Karlsruhe Institute of Technology]
标识
DOI:10.5445/ir/1000166086
摘要

Explainability techniques are rapidly being developed to improve human-AI decision-making across various cooperative work settings. Consequently, previous research has evaluated how decision-makers collaborate with imperfect AI by investigating appropriate reliance and task performance with the aim of designing more human-centered computer-supported collaborative tools. Several human-centered explainable AI (XAI) techniques have been proposed in hopes of improving decision-makers' collaboration with AI; however, these techniques are grounded in findings from previous studies that primarily focus on the impact of incorrect AI advice. Few studies acknowledge the possibility for the explanations to be incorrect even if the AI advice is correct. Thus, it is crucial to understand how imperfect XAI affects human-AI decision-making. In this work, we contribute a robust, mixed-methods user study with 136 participants to evaluate how incorrect explanations influence humans' decision-making behavior in a bird species identification task taking into account their level of expertise and an explanation's level of assertiveness. Our findings reveal the influence of imperfect XAI and humans' level of expertise on their reliance on AI and human-AI team performance. We also discuss how explanations can deceive decision-makers during human-AI collaboration. Hence, we shed light on the impacts of imperfect XAI in the field of computer-supported cooperative work and provide guidelines for designers of human-AI collaboration systems.

科研通智能强力驱动
Strongly Powered by AbleSci AI
科研通是完全免费的文献互助平台,具备全网最快的应助速度,最高的求助完成率。 对每一个文献求助,科研通都将尽心尽力,给求助人一个满意的交代。
实时播报
march完成签到 ,获得积分10
刚刚
1秒前
李先生完成签到 ,获得积分10
2秒前
无言完成签到,获得积分20
2秒前
2秒前
李健的应助被浪浪采纳,获得200
3秒前
3秒前
garrick完成签到,获得积分10
4秒前
无私的笑容完成签到,获得积分20
4秒前
一口南瓜完成签到,获得积分10
4秒前
4秒前
一只小只因完成签到 ,获得积分10
4秒前
4秒前
5秒前
斯文败类的应助被hujiaodawang采纳,获得10
5秒前
杨璇完成签到,获得积分10
6秒前
Daisy发布了新的文献求助10
6秒前
yyyt完成签到,获得积分10
7秒前
7秒前
7秒前
大师现在完成签到,获得积分10
7秒前
全没了发布了新的文献求助10
7秒前
仁爱水香完成签到,获得积分10
7秒前
陆aa完成签到 ,获得积分10
7秒前
贪玩又蓝完成签到,获得积分10
7秒前
小许的大米14完成签到,获得积分10
8秒前
SEAL完成签到,获得积分10
8秒前
SciGPT的应助被Time采纳,获得10
8秒前
8秒前
dyhhh完成签到 ,获得积分10
8秒前
勤恳幻姬发布了新的文献求助10
9秒前
9秒前
9秒前
郭永强发布了新的文献求助10
11秒前
小影完成签到 ,获得积分10
11秒前
12秒前
12秒前
屎上雕花选手完成签到,获得积分10
12秒前
13秒前
852的应助被fortuna采纳,获得10
13秒前
高分求助中
(应助此贴封号)【重要!!请各用户(尤其是新用户)详细阅读】【科研通的精品贴汇总】 10000
拉伸高分子熔体中缠结行为的模拟和小角中子散射研究 1500
The World Atlas of Wine 9th edition 1000
奈特基础组织学:配套组织病理学(第4版)(Netter's Essential Histology With Correlated Histopathology) 800
John McDowells Bildungstheorie 800
八旗制度の研究 600
Analyses de reconnaissances de dettes passées devant les échevins d'Ypres (1249-1291) 600
热门求助领域 (近24小时)
化学 材料科学 医学 生物 纳米技术 计算机科学 工程类 有机化学 化学工程 生物化学 物理 复合材料 内科学 催化作用 光电子学 人工智能 细胞生物学 无机化学 物理化学 数学
热门帖子
关注 科研通微信公众号,转发送积分 8160632
求助须知:如何正确求助?哪些是违规求助? 9555512
关于积分的说明 21728801
捐赠科研通 7750444
什么是DOI,文献DOI怎么找? 3427429
关于科研通互助平台的介绍 2552456
邀请新用户注册赠送积分活动 2471817