How to Answer Why -- Evaluating the Explanations of AI Through Mental Model Analysis

Schrills, Tim; Franke, Thomas

doi:10.48550/arxiv.2002.02526

Cited by 2 publications

(2 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This work has explored how XAI and HCXAI could enhance user folk theories by making them more accurate [12,8]. Improved folk theories have led to more effective and satisfying use of machine learning systems [22,14]. However, another perspective regarding folk theories suggests they could be utilized to better understand the user and to inform the principles and practices of HCXAI [17,11].…”

Section: Introductionmentioning

confidence: 99%

Insights from the Folk Theories of Recommender System Users

Ridley

2023

Preprint

View full text Add to dashboard Cite

show abstract

Section: Introductionmentioning

confidence: 99%

Insights from the Folk Theories of Recommender System Users

Ridley

2023

Preprint

View full text Add to dashboard Cite

show abstract

“…Such explanations allow human operators to understand autonomous actions and develop a multi-faceted conceptual model of the system's autonomy. This conceptual model includes their understanding of the system's capabilities to perform correctly under diverse conditions, its reliability for correctly completing a task (Dixon and Wickens 2006), and the degree of human trust that can be placed in the system (Rogers et al 2019;Schrills and Franke 2020). All of these factors govern human intervention behavior in a HotL system, and suggest the importance of providing rich and timely explanations of autonomous behavior.…”

Section: Introductionmentioning

confidence: 99%

Explaining Autonomous Decisions in Swarms of Human-on-the-Loop Small Unmanned Aerial Systems

Agrawal

Cleland‐Huang

2021

HCOMP

View full text Add to dashboard Cite

Rapid advancements in Artificial Intelligence have shifted the focus from traditional human-directed robots to fully autonomous ones that do not require explicit human control. These are commonly referred to as Human-on-the-Loop (HotL) systems. Transparency of HotL systems necessitates clear explanations of autonomous behavior so that humans are aware of what is happening in the environment and can understand why robots behave in a certain way. However, in complex multi-robot environments, especially those in which the robots are autonomous and mobile, humans may struggle to maintain situational awareness. Presenting humans with rich explanations of autonomous behavior tends to overload them with lots of information and negatively affect their understanding of the situation. Therefore, explaining the autonomous behavior of multiple robots creates a design tension that demands careful investigation. This paper examines the User Interface (UI) design trade-offs associated with providing timely and detailed explanations of autonomous behavior for swarms of small Unmanned Aerial Systems (sUAS) or drones. We analyze the impact of UI design choices on human awareness of the situation. We conducted multiple user studies with both inexperienced and expert sUAS operators to present our design solution and initial guidelines for designing the HotL multi-sUAS interface.

show abstract

How to Answer Why -- Evaluating the Explanations of AI Through Mental Model Analysis

Cited by 2 publications

References 0 publications

Insights from the Folk Theories of Recommender System Users

Insights from the Folk Theories of Recommender System Users

Explaining Autonomous Decisions in Swarms of Human-on-the-Loop Small Unmanned Aerial Systems

Contact Info

Product

Resources

About