Reframing explanation as an interactive medium: The EQUAS (Explainable QUestion Answering System) project

Abstract

This letter is a retrospective analysis of our team's research for the Defense Advanced Research Projects Agency Explainable Artificial Intelligence project. Our initial approach was to use salience maps, English sentences, and lists of feature names to explain the behavior of deep-learning-based discriminative systems, with particular focus on visual question answering systems. We found that presenting static explanations along with answers led to limited positive effects. By exploring various combinations of machine and human explanation production and consumption, we evolved a notion of explanation as an interactive process that takes place usually between humans and artificial intelligence systems but sometimes within the software system. We realized that by interacting via explanations people could task and adapt machine learning (ML) agents. We added affordances for editing explanations and modified the ML system to act in accordance with the edits to produce an interpretable interface to the agent. Through this interface, editing an explanation can adapt a system's performance to new, modified purposes. This deep tasking, wherein the agent knows its objective and the explanation for that objective, will be critical to enable higher levels of autonomy.explainable artificial intelligence (XAI), human/computer interaction (HCI), tasking and adapting agents, visual question answering (VQA)

An extensive review on significance of Explainable Artificial Intelligence models in discrete domains for informed decisions making

“…This is of utmost importance for facilitating better communication and understanding between machines and humans, ultimately leading to increased situational awareness. The research [48] focuses on resolving the inadequacies of current XAI applications in 3D printing in ubiquitous computing through the introduction of four novel XAI approaches: (1) a gradient bar chart featuring a baseline, (2) a gradient bar chart for groups, (3) a gradient bar chart that can be manually adjusted, and (4) a scatterplot with bidirectional capabilities. To showcase its efficacy, the suggested methodology was employed in a case study.…”

The Role of Human Knowledge in Explainable AI

“…Such human-in-the-loop approaches mainly display the explanations and the outcomes of a model to humans who are then asked to discover undesired behaviours (i.e., debugging the model) and to provide possible corrections. The effectiveness of such explainability-focused approaches is discussed by Ferguson et al [102] They report on the usefulness of explanations for human-machine interaction, while stating that augmenting explanations to support human interaction enhances their utility, creating a common ground for meaningful human-machine collaboration. They experienced the effectiveness of editable explanations, consequently modifying the machine learning system to adapt its behaviour to produce interpretable interfaces.…”