Enhancing XAI Interpretation through a Reverse Mapping from Insights to Visualizations

TL;DR

This paper introduces Reverse Mapping, a novel method that improves AI explanation interpretability by integrating user insights into visual explanations through interactive annotations and multi-view visualizations, fostering reflective interaction.

Contribution

It presents a new approach that incorporates user-derived insights into AI explanations, enhancing interpretability and user engagement in high-stakes domains.

Findings

Prototype system demonstrated in two use cases

Qualitative user feedback indicates improved interpretability

Enhances reflective interaction with AI explanations

Abstract

As AI systems become increasingly integrated into high-stakes domains, enabling users to accurately interpret model behavior is critical. While AI explanations can be provided, users often struggle to reason effectively with these explanations, limiting their ability to validate or learn from AI decisions. To address this gap, we introduce Reverse Mapping, a novel approach that enhances visual explanations by incorporating user-derived insights back into the explanation workflow. Our system extracts structured insights from free-form user interpretations using a large language model and maps them back onto visual explanations through interactive annotations and coordinated multi-view visualizations. Inspired by the verification loop in the visualization knowledge generation model, this design aims to foster more deliberate, reflective interaction with AI explanations. We demonstrate our approach in a prototype system with two use cases and qualitative user feedback.