Is the Most Accurate AI the Best Teammate? Optimizing AI for Teamwork

计算机科学 团队合作 人工智能 机器学习 任务(项目管理) 功能(生物学) 质量(理念) 运筹学 管理 进化生物学 生物 认识论 工程类 哲学 经济
作者
Gagan Bansal,Besmira Nushi,Ece Kamar,Eric Horvitz,Daniel S. Weld
出处
期刊:Proceedings of the ... AAAI Conference on Artificial Intelligence [Association for the Advancement of Artificial Intelligence]
卷期号:35 (13): 11405-11414
标识
DOI:10.1609/aaai.v35i13.17359
摘要

AI practitioners typically strive to develop the most accurate systems, making an implicit assumption that the AI system will function autonomously. However, in practice, AI systems often are used to provide advice to people in domains ranging from criminal justice and finance to healthcare. In such AI-advised decision making, humans and machines form a team, where the human is responsible for making final decisions. But is the most accurate AI the best teammate? We argue "not necessarily" --- predictable performance may be worth a slight sacrifice in AI accuracy. Instead, we argue that AI systems should be trained in a human-centered manner, directly optimized for team performance. We study this proposal for a specific type of human-AI teaming, where the human overseer chooses to either accept the AI recommendation or solve the task themselves. To optimize the team performance for this setting we maximize the team's expected utility, expressed in terms of the quality of the final decision, cost of verifying, and individual accuracies of people and machines. Our experiments with linear and non-linear models on real-world, high-stakes datasets show that the most accuracy AI may not lead to highest team performance and show the benefit of modeling teamwork during training through improvements in expected team utility across datasets, considering parameters such as human skill and the cost of mistakes. We discuss the shortcoming of current optimization approaches beyond well-studied loss functions such as log-loss, and encourage future work on AI optimization problems motivated by human-AI collaboration.
最长约 10秒,即可获得该文献文件

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
领导范儿的应助被科研通管家采纳,获得10
刚刚
所所的应助被拉塞尔....采纳,获得10
刚刚
刚刚
qdd发布了新的文献求助10
1秒前
汉堡包的应助被好的呢采纳,获得10
1秒前
1秒前
1秒前
2秒前
隐形曼青的应助被鲤鱼蓝天采纳,获得10
2秒前
专注越彬完成签到,获得积分10
2秒前
2秒前
2秒前
FashionBoy的应助被初景采纳,获得10
2秒前
科研通AI6.2的应助被Bessie采纳,获得10
3秒前
xucc的应助被刘音彤采纳,获得10
3秒前
方曦辉发布了新的文献求助10
3秒前
3秒前
3秒前
王王完成签到 ,获得积分10
3秒前
4秒前
4秒前
qqq发布了新的文献求助10
4秒前
QQ完成签到,获得积分10
5秒前
不摸鱼轩发布了新的文献求助10
5秒前
酷波er的应助被安静的雨兰采纳,获得10
5秒前
hhhh完成签到,获得积分10
5秒前
科目三的应助被x其妙采纳,获得20
5秒前
江江发布了新的文献求助10
6秒前
cfw发布了新的文献求助10
6秒前
6秒前
7秒前
幽默沛山完成签到 ,获得积分10
7秒前
Hhy1121发布了新的文献求助10
7秒前
lykkk发布了新的文献求助10
7秒前
7秒前
zsy发布了新的文献求助10
7秒前
xx2026发布了新的文献求助10
7秒前
phc完成签到,获得积分10
7秒前
yayali发布了新的文献求助10
8秒前
黄鑫发布了新的文献求助10
8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 8162816
求助须知:如何正确求助?哪些是违规求助? 9557103
关于积分的说明 21738393
捐赠科研通 7753330
什么是DOI,文献DOI怎么找? 3427963
关于科研通互助平台的介绍 2552742
邀请新用户注册赠送积分活动 2472556