Explanation as Question Answering based on Design Knowledge
This addresses the challenge of making AI explanations accessible on-demand for users who do not read manuals, though it is incremental as it applies an existing QA approach to a specific domain.
The paper tackles the problem of generating explanations for AI agents by using existing user guides as a knowledge source, presenting AskJill, a question-answering agent that automatically answers questions about the VERA interactive learning environment based on its user guide.
Explanation of an AI agent requires knowledge of its design and operation. An open question is how to identify, access and use this design knowledge for generating explanations. Many AI agents used in practice, such as intelligent tutoring systems fielded in educational contexts, typically come with a User Guide that explains what the agent does, how it works and how to use the agent. However, few humans actually read the User Guide in detail. Instead, most users seek answers to their questions on demand. In this paper, we describe a question answering agent (AskJill) that uses the User Guide for an interactive learning environment (VERA) to automatically answer questions and thereby explains the domain, functioning, and operation of VERA. We present a preliminary assessment of AskJill in VERA.