Toward Supporting Perceptual Complementarity in Human-AI Collaboration via Reflection on Unobservables
This addresses the challenge of human-AI collaboration in real-world contexts where humans lack clarity on AI's information access, though it is incremental as it explores communication guidelines without achieving clear performance gains.
The study investigated whether explicitly communicating unobservable features to humans affects how they integrate AI model outputs with their own information in decision-making, finding that such prompts can change integration but do not consistently improve performance and vary with domain expertise.
In many real world contexts, successful human-AI collaboration requires humans to productively integrate complementary sources of information into AI-informed decisions. However, in practice human decision-makers often lack understanding of what information an AI model has access to in relation to themselves. There are few available guidelines regarding how to effectively communicate about unobservables: features that may influence the outcome, but which are unavailable to the model. In this work, we conducted an online experiment to understand whether and how explicitly communicating potentially relevant unobservables influences how people integrate model outputs and unobservables when making predictions. Our findings indicate that presenting prompts about unobservables can change how humans integrate model outputs and unobservables, but do not necessarily lead to improved performance. Furthermore, the impacts of these prompts can vary depending on decision-makers' prior domain expertise. We conclude by discussing implications for future research and design of AI-based decision support tools.