Explanation as a process: user-centric construction of multi-level and multi-modal explanations

TL;DR

This paper introduces a user-centric, process-based explanation approach that combines multi-level and multi-modal explanations, enabling interactive, conversational exploration of model decisions at varying levels of detail.

Contribution

It presents a novel framework that treats explanations as an interactive process, integrating multi-modal and multi-level explanations using an interpretable ILP model and explanatory trees.

Findings

Interactive explanations improve user understanding.

Explanatory trees facilitate navigation through different detail levels.

Proof-of-concept demonstrates feasibility with semantic net data.

Abstract

In the last years, XAI research has mainly been concerned with developing new technical approaches to explain deep learning models. Just recent research has started to acknowledge the need to tailor explanations to different contexts and requirements of stakeholders. Explanations must not only suit developers of models, but also domain experts as well as end users. Thus, in order to satisfy different stakeholders, explanation methods need to be combined. While multi-modal explanations have been used to make model predictions more transparent, less research has focused on treating explanation as a process, where users can ask for information according to the level of understanding gained at a certain point in time. Consequently, an opportunity to explore explanations on different levels of abstraction should be provided besides multi-modal explanations. We present a process-based approach that combines multi-level and multi-modal explanations. The user can ask for textual explanations or visualizations through conversational interaction in a drill-down manner. We use Inductive Logic Programming, an interpretable machine learning approach, to learn a comprehensible model. Further, we present an algorithm that creates an explanatory tree for each example for which a classifier decision is to be explained. The explanatory tree can be navigated by the user to get answers of different levels of detail. We provide a proof-of-concept implementation for concepts induced from a semantic net about living beings.