Measures for explainable AI: Explanation goodness, user satisfaction, mental models, curiosity, trust, and human-AI performance

RR Hoffman, ST Mueller, G Klein… - Frontiers in Computer …, 2023 - frontiersin.org
If a user is presented an AI system that portends to explain how it works, how do we know
whether the explanation works and the user has achieved a pragmatic understanding of the …

Metrics for explainable AI: Challenges and prospects

RR Hoffman, ST Mueller, G Klein, J Litman - ar** review of patient-centered human factors
RJ Holden, VP Cornet, RS Valdez - Applied ergonomics, 2020 - Elsevier
Patient ergonomics is the application of human factors or related disciplines to study and
improve patients' and other non-professionals' performance of effortful work activities in …

Explaining reinforcement learning to mere mortals: An empirical study

A Anderson, J Dodge, A Sadarangani… - arxiv preprint arxiv …, 2019 - arxiv.org
We present a user study to investigate the impact of explanations on non-experts'
understanding of reinforcement learning (RL) agents. We investigate both a common RL …

Mental models of mere mortals with explanations of reinforcement learning

A Anderson, J Dodge, A Sadarangani… - ACM Transactions on …, 2020 - dl.acm.org
How should reinforcement learning (RL) agents explain themselves to humans not trained in
AI? To gain insights into this question, we conducted a 124-participant, four-treatment …