Explainability in Human-Agent Systems
This work provides a foundational taxonomy for researchers and practitioners in human-agent interaction, but it is incremental as it builds on existing concepts without introducing new methods or empirical results.
The paper tackles the problem of defining and categorizing explainability in Human-Agent Systems by developing a taxonomy that addresses fundamental questions about why, who, what, when, and how explanations are needed and evaluated, resulting in a structured framework for understanding and assessing explainability in such systems.
This paper presents a taxonomy of explainability in Human-Agent Systems. We consider fundamental questions about the Why, Who, What, When and How of explainability. First, we define explainability, and its relationship to the related terms of interpretability, transparency, explicitness, and faithfulness. These definitions allow us to answer why explainability is needed in the system, whom it is geared to and what explanations can be generated to meet this need. We then consider when the user should be presented with this information. Last, we consider how objective and subjective measures can be used to evaluate the entire system. This last question is the most encompassing as it will need to evaluate all other issues regarding explainability.