Explanation as Question Answering based on a Task Model of the Agent's Design

TL;DR

This paper presents a human-centered explanation approach for AI agents using a task-based model, demonstrated through an AI system linking companies and colleges with embedded question-answering for explanations.

Contribution

It introduces a design-based explanation method using a Task-Method-Knowledge model, integrated into an AI agent to generate human-understandable explanations.

Findings

Effective explanation generation through a TMK model embedded in an AI agent.

Participatory design captures relevant questions for explanations.

Demonstrated in Skillsync, linking companies and colleges.

Abstract

We describe a stance towards the generation of explanations in AI agents that is both human-centered and design-based. We collect questions about the working of an AI agent through participatory design by focus groups. We capture an agent's design through a Task-Method-Knowledge model that explicitly specifies the agent's tasks and goals, as well as the mechanisms, knowledge and vocabulary it uses for accomplishing the tasks. We illustrate our approach through the generation of explanations in Skillsync, an AI agent that links companies and colleges for worker upskilling and reskilling. In particular, we embed a question-answering agent called AskJill in Skillsync, where AskJill contains a TMK model of Skillsync's design. AskJill presently answers human-generated questions about Skillsync's tasks and vocabulary, and thereby helps explain how it produces its recommendations.