Many visualizations have been developed for explainable AI (XAI), but they often require further reasoning by users to interpret. We argue that XAI should support diagrammatic and abductive reasoning for the AI to perform hypothesis generation and evaluation to reduce the interpretability gap. We propose Diagrammatization to i) perform Peircean abductive-deductive reasoning, ii) follow domain conventions, and iii) explain with diagrams visually or verbally. We implemented DiagramNet for a clinical application to predict cardiac diagnoses from heart auscultation, and explain with shape-based murmur diagrams. In modeling studies, we found that DiagramNet not only provides faithful murmur shape explanations, but also has better prediction performance than baseline models. We further demonstrate the interpretability and trustworthiness of diagrammatic explanations in a qualitative user study with medical students, showing that clinically-relevant, diagrammatic explanations are preferred over technical saliency map explanations. This work contributes insights into providing domain-conventional abductive explanations for user-centric XAI.

翻译：在可解释人工智能领域已开发出众多可视化方法，但这些方法往往需要用户进一步推理才能解读。我们认为，可解释AI应支持图式化推理与溯因推理，使AI能够自主生成和评估假设，从而缩小可解释性差距。我们提出图式化方法以：i）执行皮尔士溯因-演绎推理，ii）遵循领域惯例，iii）通过图形或文字形式用图式进行解释。我们基于心音听诊实现用于临床诊断的DiagramNet模型，该模型通过形态化杂音图解释心脏诊断预测。建模研究表明，DiagramNet不仅能提供准确的杂音形态解释，其预测性能也优于基线模型。我们通过面向医学生的定性用户研究进一步验证了图式化解释的可解释性与可信度，结果显示临床相关的图式化解释比技术性显著图解释更受青睐。本研究为以用户为中心的可解释AI提供符合领域惯例的溯因解释提供了重要参考。