The paper proposes a novel conceptual model to structure the design space of human-AI collaboration. The model is developed through a two-step methodology: 1) an initial design space is proposed by surveying the literature and consolidating existing definitions and conceptual frameworks, and 2) the model is iteratively refined and validated by conducting semi-structured interviews with researchers in the field.
The conceptual model is centered around three high-level aspects: agency, interaction, and adaptation. Agency refers to who is in control during the analysis process and has the responsibility of decision-making. Interaction examines the specific ways that human and AI agents communicate and collaborate. Adaptation looks at how both human and AI agents learn and improve over time.
Each of these high-level aspects is further broken down into specific dimensions that can be used to characterize human-AI collaborative systems. The authors demonstrate the applicability of the design space by utilizing it to provide a structured description of three selected human-AI systems from the literature.
The proposed conceptual model aims to unify the diverse design considerations in the field of human-AI collaboration under a single comprehensive framework. It provides a solution for researchers and experts to reason about their systems, design choices, and conceptual frameworks in a systematic way.
إلى لغة أخرى
من محتوى المصدر
arxiv.org
الرؤى الأساسية المستخلصة من
by Steffen Holt... في arxiv.org 04-19-2024
https://arxiv.org/pdf/2404.12056.pdfاستفسارات أعمق