Weight of Evidence as a Basis for Human-Oriented Explanations

2019/10/29 by David Alvarez-Melis, Hal Daumé, Alvarez-Melis, David +6 · 1 citation
Arts and Humanities · Computer Science · Decision Sciences · Mathematics · #Artificial Intelligence (cs.AI) #Explainable Artificial Intelligence (XAI) #FOS: Computer and information sciences #Machine Learning (cs.LG) #Machine Learning (stat.ML) #Meta-analysis and systematic reviews #Philosophy and History of Science #cs.AI #cs.LG #stat.ML

paper · pdf · doi:10.48550/arxiv.1910.13503

Human-Centric Machine Learning (HCML) Workshop @ NeurIPS 2019

arxiv created 2019/10/29 · openalex publication_date 2019/10/29 · arxiv updated 2019/10/31 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

Interpretability is an elusive but highly sought-after characteristic of modern machine learning methods. Recent work has focused on interpretability via explanations, which justify individual model predictions. In this work, we take a step towards reconciling machine explanations with those that humans produce and prefer by taking inspiration from the study of explanation in philosophy, cognitive science, and the social sciences. We identify key aspects in which these human explanations differ from current machine explanations, distill them into a list of desiderata, and formalize them into a framework via the notion of weight of evidence from information theory. Finally, we instantiate this framework in two simple applications and show it produces intuitive and comprehensible explanations.

Citations

• Studies in the Logic of Explanation
• The base-rate fallacy in probability judgments
• Towards Robust Interpretability with Self-Explaining Neural Networks
• Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Maps
• On a Method to Measure Supervised Multiclass Model’s Interpretability: Application to Degradation Diagnosis (Short Paper)
• Variational Inference with Normalizing Flows

Cited by

• CARDIUM: Congenital Anomaly Recognition with Diagnostic Images and Unified Medical records

Related

• From Human Explanation to Model Interpretability: A Framework Based on Weight of Evidence
• How do Humans Understand Explanations from Machine Learning Systems? An Evaluation of the Human-Interpretability of Explanation
• Evaluating Explanations: An Explanatory Virtues Framework for Mechanistic Interpretability -- The Strange Science Part I.ii
• What Makes a Good Explanation?: A Harmonized View of Properties of Explanations
• An Evaluation of the Human-Interpretability of Explanation