Role of Human-AI Interaction in Selective Prediction

被引:0
|
作者
Bondi, Elizabeth [1 ]
Koster, Raphael [2 ]
Sheahan, Hannah [2 ]
Chadwick, Martin [2 ]
Bachrach, Yoram [2 ]
Cemgil, Taylan [2 ]
Paquet, Ulrich [2 ]
Dvijotham, Krishnamurthy [3 ]
机构
[1] Harvard Univ, Cambridge, MA 02138 USA
[2] DeepMind, London, England
[3] Google Brain, Mountain View, CA USA
关键词
D O I
暂无
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Recent work has shown the potential benefit of selective prediction systems that can learn to defer to a human when the predictions of the AI are unreliable, particularly to improve the reliability of AI systems in high-stakes applications like healthcare or conservation. However, most prior work assumes that human behavior remains unchanged when they solve a prediction task as part of a human-AI team as opposed to by themselves. We show that this is not the case by performing experiments to quantify human-AI interaction in the context of selective prediction. In particular, we study the impact of communicating different types of information to humans about the AI system's decision to defer. Using realworld conservation data and a selective prediction system that improves expected accuracy over that of the human or AI system working individually, we show that this messaging has a significant impact on the accuracy of human judgements. Our results study two components of the messaging strategy: 1) Whether humans are informed about the prediction of the AI system and 2) Whether they are informed about the decision of the selective prediction system to defer. By manipulating these messaging components, we show that it is possible to significantly boost human performance by informing the human of the decision to defer, but not revealing the prediction of the AI. We therefore show that it is vital to consider how the decision to defer is communicated to a human when designing selective prediction systems, and that the composite accuracy of a human-AI team must be carefully evaluated using a human-in-the-loop framework.
引用
收藏
页码:5286 / 5294
页数:9
相关论文
共 50 条
  • [31] Playing with Dezgo: Adapting Human-AI Interaction to the Context of Play
    Villareale, Jennifer
    Cimolino, Gabriele
    Gomme, Daniel
    [J]. PROCEEDINGS OF THE 18TH INTERNATIONAL CONFERENCE ON THE FOUNDATIONS OF DIGITAL GAMES, FDG 2023, 2023,
  • [32] Ethical management of human-AI interaction: Theory development review
    Heyder, Teresa
    Passlack, Nina
    Posegga, Oliver
    [J]. JOURNAL OF STRATEGIC INFORMATION SYSTEMS, 2023, 32 (03):
  • [33] A systematic review of human-AI interaction in autonomous ship system
    Veitch, Erik
    Alsos, Ole Andreas
    [J]. SAFETY SCIENCE, 2022, 152
  • [34] Exploring a Behavioral Model of "Positive Friction" in Human-AI Interaction
    Chen, Zeya
    Schmidt, Ruth
    [J]. DESIGN, USER EXPERIENCE, AND USABILITY, DUXU 2024, PT II, 2024, 14713 : 3 - 22
  • [35] From explainable to interactive AI: A literature review on current trends in human-AI interaction
    Raees, Muhammad
    Meijerink, Inge
    Lykourentzou, Ioanna
    Khan, Vassilis-Javed
    Papangelis, Konstantinos
    [J]. INTERNATIONAL JOURNAL OF HUMAN-COMPUTER STUDIES, 2024, 189
  • [36] Trustworthy human-AI partnerships
    Ramchurn, Sarvapali D.
    Stein, Sebastian
    Jennings, Nicholas R.
    [J]. ISCIENCE, 2021, 24 (08)
  • [37] SatisfAI: A Serious Tabletop Game to Reveal Human-AI Interaction Dynamics
    Kim, Moon K.
    Trewhitt, Ethan
    [J]. ADAPTIVE INSTRUCTIONAL SYSTEMS, AIS 2022, 2022, 13332 : 174 - 189
  • [38] Trust in Human-AI Interaction: Scoping Out Models, Measures, and Methods
    Ueno, Takane
    Sawa, Yuto
    Kim, Yeongdae
    Urakami, Jacqueline
    Oura, Hiroki
    Seaborn, Katie
    [J]. EXTENDED ABSTRACTS OF THE 2022 CHI CONFERENCE ON HUMAN FACTORS IN COMPUTING SYSTEMS, CHI 2022, 2022,
  • [39] eXtended Artificial Intelligence: New Prospects of Human-AI Interaction Research
    Wienrich, Carolin
    Latoschik, Marc Erich
    [J]. FRONTIERS IN VIRTUAL REALITY, 2021, 2
  • [40] A Review on Human-AI Interaction in Machine Learning and Insights for Medical Applications
    Maadi, Mansoureh
    Akbarzadeh Khorshidi, Hadi
    Aickelin, Uwe
    [J]. INTERNATIONAL JOURNAL OF ENVIRONMENTAL RESEARCH AND PUBLIC HEALTH, 2021, 18 (04) : 1 - 21