"Why Should I Trust You?"

作者：Marco Túlio Ribeiro, Sameer Singh, Carlos Guestrin · 年份：2016 · DOI：10.1145/2939672.2939778 · 被引用次数：16381 · 研究领域：Explainable Artificial Intelligence (XAI)、Adversarial Robustness in Machine Learning、Machine Learning in Healthcare

Despite widespread adoption, machine learning models remain mostly black boxes. Understanding the reasons behind predictions is, however, quite important in assessing trust, which is fundamental if one plans to take action based on a prediction, or when choosing whether to deploy a new model. Such understanding also provides insights into the model, which can be used to transform an untrustworthy model or prediction into a trustworthy one.