Don't Explain without Verifying Veracity: An Evaluation of Explainable AI with Video Activity Recognition
This addresses the challenge of ensuring that explanations in AI systems are truthful and meaningful for users, particularly in video activity recognition, but it is incremental as it builds on existing evaluation methods.
The paper investigates how the accuracy of explanations in explainable AI systems affects user performance and agreement, finding that low veracity explanations significantly reduce both compared to accurate explanations or no explanations.
Explainable machine learning and artificial intelligence models have been used to justify a model's decision-making process. This added transparency aims to help improve user performance and understanding of the underlying model. However, in practice, explainable systems face many open questions and challenges. Specifically, designers might reduce the complexity of deep learning models in order to provide interpretability. The explanations generated by these simplified models, however, might not accurately justify and be truthful to the model. This can further add confusion to the users as they might not find the explanations meaningful with respect to the model predictions. Understanding how these explanations affect user behavior is an ongoing challenge. In this paper, we explore how explanation veracity affects user performance and agreement in intelligent systems. Through a controlled user study with an explainable activity recognition system, we compare variations in explanation veracity for a video review and querying task. The results suggest that low veracity explanations significantly decrease user performance and agreement compared to both accurate explanations and a system without explanations. These findings demonstrate the importance of accurate and understandable explanations and caution that poor explanations can sometimes be worse than no explanations with respect to their effect on user performance and reliance on an AI system.