The growing capabilities of AI models are leading to their wider use, including in safety-critical domains. Explainable AI (XAI) aims to make these models safer to use by making their inference process more transparent. However, current explainability methods are seldom evaluated in the way they are intended to be used: by real-world end users. To address this, we conducted a large-scale user study with 85 healthcare practitioners in the context of human-AI collaborative chest X-ray analysis. We evaluated three types of explanations: visual explanations (saliency maps), natural language explanations, and a combination of both modalities. We specifically examined how different explanation types influence users depending on whether the AI advice and explanations are factually correct. We find that text-based explanations lead to significant over-reliance, which is alleviated by combining them with saliency maps. We also observe that the quality of explanations, that is, how much factually correct information they entail, and how much this aligns with AI correctness, significantly impacts the usefulness of the different explanation types.

翻译：随着AI模型能力的不断增强，其应用范围日益扩大，甚至延伸至安全关键领域。可解释人工智能（XAI）旨在通过提高模型推理过程的透明度来增强其使用安全性。然而，当前的可解释性方法很少在其预期使用场景——即由真实终端用户实际运用——中得到评估。为解决这一问题，我们在人机协作胸片分析的背景下，开展了一项涉及85名医疗从业者的大规模用户研究。我们评估了三种解释类型：视觉解释（显著图）、自然语言解释以及两种模态的组合。我们特别考察了当AI建议与解释在事实正确性不同时，各类解释如何影响用户决策。研究发现，基于文本的解释会导致显著的过度依赖，而将其与显著图结合可缓解此现象。我们还观察到，解释的质量——即其包含的事实正确信息量及其与AI正确性的匹配程度——对不同解释类型的实用性具有显著影响。