Requirements for Explainability and Acceptance of Artificial Intelligence in Collaborative Work

TL;DR

This literature analysis identifies key information needs and interaction methods that influence the explainability and acceptance of AI in safety-critical collaborative work, emphasizing user-specific requirements and trust-building strategies.

Contribution

It provides a comprehensive review of 48 articles on user information needs and interaction methods for AI explainability and acceptance, highlighting differences between developers and end users.

Findings

Developers need insights into AI internal operations.

End users require understandable AI results and behavior.

Trust is enhanced by human-like interaction and transparency about limitations.

Abstract

The increasing prevalence of Artificial Intelligence (AI) in safety-critical contexts such as air-traffic control leads to systems that are practical and efficient, and to some extent explainable to humans to be trusted and accepted. The present structured literature analysis examines n = 236 articles on the requirements for the explainability and acceptance of AI. Results include a comprehensive review of n = 48 articles on information people need to perceive an AI as explainable, the information needed to accept an AI, and representation and interaction methods promoting trust in an AI. Results indicate that the two main groups of users are developers who require information about the internal operations of the model and end users who require information about AI results or behavior. Users' information needs vary in specificity, complexity, and urgency and must consider context, domain knowledge, and the user's cognitive resources. The acceptance of AI systems depends on information about the system's functions and performance, privacy and ethical considerations, as well as goal-supporting information tailored to individual preferences and information to establish trust in the system. Information about the system's limitations and potential failures can increase acceptance and trust. Trusted interaction methods are human-like, including natural language, speech, text, and visual representations such as graphs, charts, and animations. Our results have significant implications for future human-centric AI systems being developed. Thus, they are suitable as input for further application-specific investigations of user needs.