# Weight of Evidence as a Basis for Human-Oriented Explanations

arXiv: https://arxiv.org/abs/1910.13503 · HTML: https://mlsanity.com/paper/1910.13503/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 29 Oct 2019.

## Built on by (most cited first, 10 of 10)

- [The Out-of-Distribution Problem in Explainability and Search Methods for Feature Importance Explanations](https://mlsanity.com/paper/2106.00786/) (2021)
- [Do People Engage Cognitively with AI? Impact of AI Assistance on Incidental Learning](https://mlsanity.com/paper/2202.05402/) (2022)
- [Near-Optimal Explainable k-Means for All Dimensions](https://mlsanity.com/paper/2106.15566/) (2021)
- [Explainability Is in the Mind of the Beholder: Establishing the Foundations of Explainable Artificial Intelligence](https://mlsanity.com/paper/2112.14466/) (2021)
- [Saliency Map Verbalization: Comparing Feature Importance Representations from Model-free and Instruction-based Methods](https://mlsanity.com/paper/2210.07222/) (2022)
- [Mediators: Conversational Agents Explaining NLP Model Behavior](https://mlsanity.com/paper/2206.06029/) (2022)
- [A General Search-based Framework for Generating Textual Counterfactual Explanations](https://mlsanity.com/paper/2211.00369/) (2022)
- [CARDIUM: Congenital Anomaly Recognition with Diagnostic Images and Unified Medical records](https://mlsanity.com/paper/2510.15208/) (2025)
- [Generating Explanations from Deep Reinforcement Learning Using Episodic Memory](https://mlsanity.com/paper/2205.08926/) (2022)
- [Optimal and efficient text counterfactuals using Graph Neural Networks](https://mlsanity.com/paper/2408.01969/) (2024)

## Abstract (arXiv)

Interpretability is an elusive but highly sought-after characteristic of modern machine learning methods. Recent work has focused on interpretability via textitexplanations, 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 textitweight of evidence from information theory. Finally, we instantiate this framework in two simple applications and show it produces intuitive and comprehensible explanations.