Co-creating a globally interpretable model with human input

TL;DR

This paper presents a novel approach for human-AI collaboration in building interpretable Boolean decision rule models, emphasizing joint decision logic construction rather than outcome aggregation.

Contribution

It introduces a method for co-creating decision models with human input, focusing on logical conditions and templates to enhance interpretability.

Findings

Demonstrated the approach with two example applications.

Highlighted the benefits of joint decision logic construction.

Discussed challenges in human-AI collaborative modeling.

Abstract

We consider an aggregated human-AI collaboration aimed at generating a joint interpretable model. The model takes the form of Boolean decision rules, where human input is provided in the form of logical conditions or as partial templates. This focus on the combined construction of a model offers a different perspective on joint decision making. Previous efforts have typically focused on aggregating outcomes rather than decisions logic. We demonstrate the proposed approach through two examples and highlight the usefulness and challenges of the approach.