Recommendations for the Empirical Assessment  of Human-AI Work Systems: A Contribution to AI Measurement Science

Hoffman, Robert M.; Klein, Gary; Clancey, William J.

doi:10.31234/osf.io/z3yek

Search citation statements

Order By: Relevance

Paper Sections

Select...

Appendix B Criticism: On Decision-level (Local) and Model-le...1

Citation Types

Supporting

Mentioning

Contrasting

Year Published

2023

Publication Types

Select...

Article1

Relationship

Self Cite0

Independent1

Authors

Journals

Cited by 1 publication

(1 citation statement)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Given this conclusion, we argue that "decision-level" categorization is potentially misleading as a description of explanation methods. This argument has also been discussed by Hoffman et al (2020).…”

Section: Appendix B Criticism: On Decision-level (Local) and Model-le...mentioning

confidence: 66%

Diagnosing AI Explanation Methods with Folk Concepts of Behavior

Jacovi,

Bastings,

Gehrmann

et al. 2023

jair

View full text Add to dashboard Cite

We investigate a formalism for the conditions of a successful explanation of AI. We consider “success” to depend not only on what information the explanation contains, but also on what information the human explainee understands from it. Theory of mind literature discusses the folk concepts that humans use to understand and generalize behavior. We posit that folk concepts of behavior provide us with a “language” that humans understand behavior with. We use these folk concepts as a framework of social attribution by the human explainee—the information constructs that humans are likely to comprehend from explanations—by introducing a blueprint for an explanatory narrative (Figure 1) that explains AI behavior with these constructs. We then demonstrate that many XAI methods today can be mapped to folk concepts of behavior in a qualitative evaluation. This allows us to uncover their failure modes that prevent current methods from explaining successfully—i.e., the information constructs that are missing for any given XAI method, and whose inclusion can decrease the likelihood of misunderstanding AI behavior.

show abstract

Section: Appendix B Criticism: On Decision-level (Local) and Model-le...mentioning

confidence: 66%