Supporting Data-Frame Dynamics in AI-assisted Decision Making

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Zheng, Chengbo, Miller, Tim, Bialkowski, Alina, Soyer, H Peter, Janda, Monika
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915253420294144
author Zheng, Chengbo
Miller, Tim
Bialkowski, Alina
Soyer, H Peter
Janda, Monika
author_facet Zheng, Chengbo
Miller, Tim
Bialkowski, Alina
Soyer, H Peter
Janda, Monika
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2504_15894
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Supporting Data-Frame Dynamics in AI-assisted Decision Making
Zheng, Chengbo
Miller, Tim
Bialkowski, Alina
Soyer, H Peter
Janda, Monika
Human-Computer Interaction
Artificial Intelligence
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.
title Supporting Data-Frame Dynamics in AI-assisted Decision Making
topic Human-Computer Interaction
Artificial Intelligence
url https://arxiv.org/abs/2504.15894