Watch Out for Updates: Understanding the Effects of Model Explanation Updates in AI-Assisted Decision Making
Watch Out for Updates: Understanding the Effects of Model Explanation Updates in AI-Assisted Decision Making
复制标题
DOI：
10.1145/3544548.3581366
复制
发表时间：
2023-04
期刊：
影响因子：
--
通讯作者：
Xinru Wang;Ming Yin
中科院分区：
文献类型：
--
作者：
Xinru Wang;Ming Yin
人工智能解释越来越多地用于帮助人们在人工智能辅助决策中更好地利用人工智能建议。尽管由于人工智能模型的更新，人工智能的解释可能会随着时间的推移而发生变化，但人们对这些变化如何影响人们对该模型的看法和使用知之甚少。在本文中，我们研究了模型更新前后人工智能解释之间不同程度的相似性如何影响人们对人工智能模型的信任和满意度。我们在两种决策环境中进行了随机人体实验，其中人们具有不同水平的领域知识。我们的结果表明，模型更新期间人工智能解释的变化不会影响人们采用人工智能建议的倾向。然而，它们可能会通过改变人们感知的模型准确性以及人工智能解释与先验知识的一致性来改变人们对人工智能模型的主观信任和满意度。
AI explanations have been increasingly used to help people better utilize AI recommendations in AI-assisted decision making. While AI explanations may change over time due to updates of the AI model, little is known about how these changes may affect people’s perceptions and usage of the model. In this paper, we study how varying levels of similarity between the AI explanations before and after a model update affects people’s trust in and satisfaction with the AI model. We conduct randomized human-subject experiments on two decision making contexts where people have different levels of domain knowledge. Our results show that changes in AI explanation during the model update do not affect people’s tendency to adopt AI recommendations. However, they may change people’s subjective trust in and satisfaction with the AI model via changing both their perceived model accuracy and perceived consistency of AI explanations with their prior knowledge.