Towards Directive Explanations: Crafting Explainable AI Systems for Actionable Human-AI Interactions

Abstract

With Artificial Intelligence (AI) becoming ubiquitous in every application domain, the need for explanations is paramount to enhance transparency and trust among non-technical users. Despite the potential shown by Explainable AI (XAI) for enhancing understanding of complex AI systems, most XAI methods are designed for technical AI experts rather than non-technical consumers. Consequently, such explanations are overwhelmingly complex and seldom guide users in achieving their desired predicted outcomes. This paper presents ongoing research for crafting XAI systems tailored to guide users in achieving desired outcomes through improved human-AI interactions. This paper highlights the research objectives and methods, key takeaways and implications learned from user studies. It outlines open questions and challenges for enhanced human-AI collaboration, which the author aims to address in future work.

arXiv commentPre-print version. Please check the published version in ACM CHI 2024 from the related DOI

References in corpus (8)

• From Anecdotal Evidence to Quantitative Evaluation Methods: A Systematic Review on Evaluating Explainable AI
• The What-If Tool: Interactive Probing of Machine Learning Models
• Actionable Recourse in Linear Classification
• explAIner: A Visual Analytics Framework for Interactive and Explainable Machine Learning
• Interpretable Classification Models for Recidivism Prediction
• Explainable Artificial Intelligence Approaches: A Survey
• Directive Explanations for Monitoring the Risk of Diabetes Onset: Introducing Directive Data-Centric Explanations and Combinations to Support What-If Explorations
• Directive Explanations for Actionable Explainability in Machine Learning Applications

Cited by in corpus (4)

• Representation Debiasing of Generated Data Involving Domain Experts
• An Explanatory Model Steering System for Collaboration between Domain Experts and AI
• Show Me How: Benefits and Challenges of Agent-Augmented Counterfactual Explanations for Non-Expert Users
• Explanatory Debiasing: Involving Domain Experts in the Data Generation Process to Mitigate Representation Bias in AI Systems