Explaining and Improving Information Complementarities in Multi-Agent Decision-making

TL;DR

This paper introduces a decision-theoretic framework and a novel explanation method, ILIV-SHAP, to enhance human-AI collaboration by identifying and leveraging complementary information for improved decision-making.

Contribution

It develops a framework for characterizing information value and introduces ILIV-SHAP, a new explanation technique tailored for highlighting human-AI complementary information.

Findings

ILIV-SHAP improves error reduction in human-AI decisions

Framework effectively identifies opportunities for exploiting information

Validated on medical and deepfake detection tasks

Abstract

Multiple agents are increasingly combined to make decisions with the expectation of achieving complementary performance, where the decisions they make together outperform those made individually. However, knowing how to improve the performance of collaborating agents requires knowing what information and strategies each agent employs. With a focus on human-AI pairings, we contribute a decision-theoretic framework for characterizing the value of information. By defining complementary information, our approach identifies opportunities for agents to better exploit available information in AI-assisted decision workflows. We present a novel explanation technique (ILIV-SHAP) that adapts SHAP explanations to highlight human-complementing information. We validate the effectiveness of our framework and ILIV-SHAP through a study of human-AI decision-making, and demonstrate the framework on examples from chest X-ray diagnosis and deepfake detection. We find that presenting ILIV-SHAP with AI predictions leads to reliably greater reductions in error over non-AI assisted decisions more than vanilla SHAP.