Explanation as Question Answering based on a Task Model of the Agent's Design
This work addresses the need for better interpretability in AI systems, particularly for stakeholders in workforce development, but it appears incremental as it builds on existing modeling and explanation techniques.
The paper tackles the problem of generating human-centered explanations for AI agents by using a Task-Method-Knowledge model to capture design details, and demonstrates this approach in Skillsync, an agent for linking companies and colleges, where an embedded question-answering agent helps explain recommendations.
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.