Active Trust Management

Fitzhugh, Elisabeth; Hoffman, Robert R.; Miller, Joseph D.

doi:10.1201/9781315549637-11

Cited by 2 publications

(2 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…2); deceptive (z ¼ 2.532, p < 0.05, r ¼ 0.45), underhanded (z ¼ 2.076, p < 0.05, r ¼ 0.37), suspicious (z ¼ 3.749, p < 0.01, r ¼ 0.66), wary (z ¼ 3.306, p < 0.01, r ¼ 0.58) and harmful (z ¼ 2.864, p < 0.01, r ¼ 0.51). This may be attributed to drivers not having yet learnt the competence limits of the technology (Fitzhugh et al, 2011) or having experienced some of the issues highlighted above (e.g. unsafe lane offering).…”

Section: Driver Trustmentioning

confidence: 91%

Keep the driver in control: Automating automobiles of the future

2016

View full text Add to dashboard Cite

Section: Driver Trustmentioning

confidence: 91%

Keep the driver in control: Automating automobiles of the future

2016

View full text Add to dashboard Cite

“…Trust in automation is of concern in computer science and cognitive systems engineering, as well as in the popular media (e.g., Hoffman, 1989;Shadbolt, 2002;Lee and See, 2004;Huynh et al, 2006;Woods and Hollnagel, 2006;Merritt and Ilgen, 2008;Hoffman et al, 2009Hoffman et al, , 2013Naone, 2009;Montague, 2010;Fitzhugh et al, 2011;Kucala, 2013;Merritt et al, 2013Merritt et al, , 2015Chancey et al, 2015;Hoff and Bashir, 2015;Pop et al, 2015;Wickens et al, 2015). Trust is implicated in many ways in AI system development.…”

Section: Measuring Trust In the Xai Contextmentioning

confidence: 99%

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

Hoffman

Klein²,

Litman

2023

Front. Comput. Sci.

View full text Add to dashboard Cite

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 AI? This question entails some key concepts of measurement such as explanation goodness and trust. We present methods for enabling developers and researchers to: (1) Assess the a priori goodness of explanations, (2) Assess users' satisfaction with explanations, (3) Reveal user's mental model of an AI system, (4) Assess user's curiosity or need for explanations, (5) Assess whether the user's trust and reliance on the AI are appropriate, and finally, (6) Assess how the human-XAI work system performs. The methods we present derive from our integration of extensive research literatures and our own psychometric evaluations. We point to the previous research that led to the measurement scales which we aggregated and tailored specifically for the XAI context. Scales are presented in sufficient detail to enable their use by XAI researchers. For Mental Model assessment and Work System Performance, XAI researchers have choices. We point to a number of methods, expressed in terms of methods' strengths and weaknesses, and pertinent measurement issues.

show abstract

Active Trust Management

Cited by 2 publications

References 0 publications

Keep the driver in control: Automating automobiles of the future

Keep the driver in control: Automating automobiles of the future

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

Contact Info

Product

Resources

About