High stakes decision-making often requires a continuous interplay between evolving evidence and shifting hypotheses, a dynamic that is not well supported by current AI decision support systems. In this paper, we introduce a mixed-initiative framework for AI assisted decision making that is grounded in the data-frame theory of sensemaking and the evaluative AI paradigm. Our approach enables both humans and AI to collaboratively construct, validate, and adapt hypotheses. We demonstrate our framework with an AI-assisted skin cancer diagnosis prototype that leverages a concept bottleneck model to facilitate interpretable interactions and dynamic updates to diagnostic hypotheses.
@article{arxiv.2504.15894,
title = {Supporting Data-Frame Dynamics in AI-assisted Decision Making},
author = {Chengbo Zheng and Tim Miller and Alina Bialkowski and H Peter Soyer and Monika Janda},
journal= {arXiv preprint arXiv:2504.15894},
year = {2025}
}
Comments
Presented at the 2025 ACM Workshop on Human-AI Interaction for Augmented Reasoning, Report Number: CHI25-WS-AUGMENTED-REASONING