Weight of Evidence as a Basis for Human-Oriented Explanations

10/29/2019
by   David Alvarez-Melis, et al.
53

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.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
04/27/2021

A Human-Centered Interpretability Framework Based on Weight of Evidence

In this paper, we take a human-centered approach to interpretable machin...
research
06/22/2021

On the Diversity and Limits of Human Explanations

A growing effort in NLP aims to build datasets of human explanations. Ho...
research
12/06/2021

HIVE: Evaluating the Human Interpretability of Visual Explanations

As machine learning is increasingly applied to high-impact, high-risk do...
research
06/03/2020

From Probability to Consilience: How Explanatory Values Implement Bayesian Reasoning

Recent work in cognitive science has uncovered a diversity of explanator...
research
03/01/2021

ToxCCIn: Toxic Content Classification with Interpretability

Despite the recent successes of transformer-based models in terms of eff...
research
07/01/2020

In-Distribution Interpretability for Challenging Modalities

It is widely recognized that the predictions of deep neural networks are...
research
04/13/2023

Evaluating the Robustness of Interpretability Methods through Explanation Invariance and Equivariance

Interpretability methods are valuable only if their explanations faithfu...

Please sign up or login with your details

Forgot password? Click here to reset