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

IS AI GROUND TRUTH REALLY TRUE? THE DANGERS OF TRAINING AND EVALUATING AI TOOLS BASED ON EXPERTS' KNOW-WHAT1

Lebovitz, Sarah*; Levine, Natalia; Lifshitz-Assaf, Hila
MIS QUARTERLY2021-9DOI: 10.25300/MISQ/2021/16564
89被引4阅读
引用收藏
分享

摘要

Organizational decision-makers need to evaluate AI tools in light of increasing claims that such tools outperform human experts. Yet, measuring the quality of knowledge work is challenging, raising the question of how to evaluate AI performance in such contexts. We investigate this question through a field study of a major U.S. hospital, observing how managers evaluated five different machine-learning (ML) based AI tools. Each tool reported high performance according to standard AI accuracy measures, which were based on ground truth labels provided by qualified experts. Trying these tools out in practice, however, revealed that none of them met expectations. Searching for explanations, managers began confronting the high uncertainty of experts' know-what knowledge captured in ground truth labels used to train and validate ML models. In practice, experts address this uncertainty by drawing on rich know-how practices, which were not incorporated into these ML-based tools. Discovering the disconnect between AI's know-what and experts' know-how enabled managers to better understand the risks and benefits of each tool. This study shows dangers of treating ground truth labels used in ML models objectively when the underlying knowledge is uncertain. We outline implications of our study for developing, training, and evaluating AI for knowledge work.

学科与关键词

关键词
Artificial intelligenceevaluation uncertainty new technology professional knowledgework innovation know-how medical diagnosisground truth
相关
加载中…
  • WHEN THE MACHINE MEETS THE EXPERT: AN ETHNOGRAPHY OF DEVELOPING AI FOR HIRING
    van den Broek, Elmira*; Sergeeva, Anastasia; Huysman, MarleenMIS QUARTERLY, 2021, 45(3): 1557-1580.被引 124
  • Assessing the communication gap between AI models and healthcare professionals: Explainability, utility and trust in AI-driven clinical decision-making
    Wysocki, Oskar*; Davies, Jessica Katharine; Vigo, Markel; Armstrong, Anne Caroline; Landers, Donal; Lee, Rebecca; Freitas, AndreArtificial Intelligence, 2023, 316: 103839.被引 28
  • Trusting Intelligent Automation in Expert Work: Accounting Practitioners' Experiences and Perceptions
    Ala-Luopa, Saara*; Olsson, Thomas; Vaananen, Kaisa; Hartikainen, Maria; Makkonen, JoukoCOMPUTER SUPPORTED COOPERATIVE WORK-THE JOURNAL OF COLLABORATIVE COMPUTING AND WORK PRACTICES, 2024, 33(4): 1343-1371.
查看全部 →

发表信息

论文状态
公开发表
期刊
MIS QUARTERLY
发表日期
2021-09
卷期
第 45 卷, 第 3 期
页码
1501-1526
DOI
10.25300/MISQ/2021/16564
语言
ENGLISH
期刊收录
NSL
期刊等级
2区
成果收录
SCIE

作者

  • L

    Lebovitz, Sarah (通讯) (第一作者)

  • L

    Levine, Natalia

查看全部 3 位作者收起作者
  • L

    Lifshitz-Assaf, Hila

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