Supporting Reflection and Forward-Looking Reasoning With Data-Driven Questions

TL;DR

This paper explores methods to enhance critical thinking in AI-assisted decision-making by developing data-driven questions, including a taxonomy, a prototype, question generation techniques, and a cognitive engagement scale.

Contribution

It introduces a question taxonomy, a prototype for medical decision support, a question generation method using large language models, and a scale for measuring cognitive engagement.

Findings

Clinicians provided feedback on the prototype.

A method for generating questions with large language models was developed.

A scale for measuring cognitive engagement was proposed.

Abstract

Many generative AI systems as well as decision-support systems (DSSs) provide operators with predictions or recommendations. Various studies show, however, that people can mistakenly adopt the erroneous results presented by those systems. Hence, it is crucial to promote critical thinking and reflection during interaction. One approach we are focusing on involves encouraging reflection during machine-assisted decision-making by presenting decision-makers with data-driven questions. In this short paper, we provide a brief overview of our work in that regard, namely: 1) the development of a question taxonomy, 2) the development of a prototype in the medical domain and the feedback received from clinicians, 3) a method for generating questions using a large language model, and 4) a proposed scale for measuring cognitive engagement in human-AI decision-making. In doing so, we contribute to the discussion about the design, development, and evaluation of tools for thought, i.e., AI systems that provoke critical thinking and enable novel ways of sense-making.