Improving Human-AI Collaboration With Descriptions of AI Behavior

被引：6
作者：
Cabrera Á.A. [1 ]
Perer A. [1 ]
Hong J.I. [1 ]
机构：
[1] Carnegie Mellon University, Pittsburgh, PA
来源：
Proc. ACM Hum. Comput. Interact. | 2023年 / CSCW1卷
基金：
美国国家科学基金会;
关键词：
human-AI collaboration; machine learning;
D O I：
10.1145/3579612
中图分类号：
学科分类号：
摘要：
People work with AI systems to improve their decision making, but often under- or over-rely on AI predictions and perform worse than they would have unassisted. To help people appropriately rely on AI aids, we propose showing them behavior descriptions, details of how AI systems perform on subgroups of instances. We tested the efficacy of behavior descriptions through user studies with 225 participants in three distinct domains: fake review detection, satellite image classification, and bird classification. We found that behavior descriptions can increase human-AI accuracy through two mechanisms: helping people identify AI failures and increasing people's reliance on the AI when it is more accurate. These findings highlight the importance of people's mental models in human-AI collaboration and show that informing people of high-level AI behaviors can significantly improve AI-assisted decision making. © 2023 Owner/Author.
引用
收藏
相关论文
共 66 条
[1]  
Akhtar N., Mian A., Threat of Adversarial Attacks on Deep Learning in Computer Vision: A Survey, IEEE Access, 6, pp. 14410-14430, (2018)
[2]  
Anderson J.R., Matessa M., Lebiere C., ACT-R: A Theory of Higher Level Cognition and Its Relation to Visual Attention, Human-Computer Interaction, 12, 4, pp. 439-462, (1997)
[3]  
Bansal G., Nushi B., Kamar E., Lasecki W.S., Weld D.S., Horvitz E., Beyond Accuracy: The Role of Mental Models in Human-AI Team Performance, Proceedings of the AAAI Conference on Human Computation and Crowdsourcing, 7, 1, (2019)
[4]  
Bansal G., Nushi B., Kamar E., Weld D.S., Lasecki W.S., Horvitz E., Updates in Human-AI Teams: Understanding and Addressing the Performance/Compatibility Tradeoff, Proceedings of the AAAI Conference on Artificial Intelligence, 33, pp. 2429-2437, (2019)
[5]  
Bansal G., Wu T., Zhou J., Does the Whole Exceed Its Parts? The Effect of AI Explanations on Complementary Team Performance, Proceedings of the 2021 CHI Conference on Human Factors in Computing Systems, pp. 1-26, (2021)
[6]  
Brown T.B., Mann B., Ryder N., Subbiah M., Kaplan J., Dhariwal P., Neelakantan A., Shyam P., Sastry G., Askell A., Agarwal S., Herbert-Voss A., Krueger G., Henighan T., Child R., Ramesh A., Ziegler D.M., Wu J., Winter C., Hesse C., Chen M., Sigler E., Litwin M., Gray S., Chess B., Clark J., Berner C., McCandlish S., Radford A., Sutskever I., Amodei D., Language Models are Few-Shot Learners, Advances in Neural Information Processing Systems, 33, pp. 1877-1901, (2020)
[7]  
Bussone A., Stumpf S., O'Sullivan D., The role of explanations on trust and reliance in clinical decision support systems, Proceedings-2015 IEEE International Conference on Healthcare Informatics, ICHI 2015, pp. 160-169, (2015)
[8]  
Bucinca Z., Barbara Malaya M., Gajos K.Z., To Trust or to Think: Cognitive Forcing Functions Can Reduce Overreliance on AI in AI-assisted Decision-making, Proceedings of the ACM on Human-Computer Interaction, 5, CSCW1, pp. 1-21, (2021)
[9]  
Alexander Cabrera A., Druck A.J., Hong J.I., Perer A., Discovering and Validating AI Errors With Crowdsourced Failure Reports, Proceedings of the ACM on Human-Computer Interaction, 5, CSCW2, pp. 1-22, (2021)
[10]  
Alexander Cabrera A., Epperson W., Hohman F., Kahng M., Morgenstern J., Horng Chau D., FairVis: Visual Analytics for Discovering Intersectional Bias in Machine Learning, 2019 IEEE Conference on Visual Analytics Science and Technology (VAST), pp. 46-56, (2019)
1234567