Explainable Generative AI (GenXAI): A Survey, Conceptualization, and Research Agenda

TL;DR

This survey explores the importance, challenges, and emerging needs for explainability in generative AI, proposing a taxonomy and future research directions to enhance understanding and trust in GenAI systems.

Contribution

It provides a comprehensive taxonomy of XAI methods for GenAI, discusses novel desiderata, and outlines a research agenda for future exploration.

Findings

Identifies key challenges in explainability for GenAI

Proposes a taxonomy of XAI mechanisms for GenAI

Suggests future research directions in XAI

Abstract

Generative AI (GenAI) marked a shift from AI being able to recognize to AI being able to generate solutions for a wide variety of tasks. As the generated solutions and applications become increasingly more complex and multi-faceted, novel needs, objectives, and possibilities have emerged for explainability (XAI). In this work, we elaborate on why XAI has gained importance with the rise of GenAI and its challenges for explainability research. We also unveil novel and emerging desiderata that explanations should fulfill, covering aspects such as verifiability, interactivity, security, and cost. To this end, we focus on surveying existing works. Furthermore, we provide a taxonomy of relevant dimensions that allows us to better characterize existing XAI mechanisms and methods for GenAI. We discuss different avenues to ensure XAI, from training data to prompting. Our paper offers a short but concise technical background of GenAI for non-technical readers, focusing on text and images to better understand novel or adapted XAI techniques for GenAI. However, due to the vast array of works on GenAI, we decided to forego detailed aspects of XAI related to evaluation and usage of explanations. As such, the manuscript interests both technically oriented people and other disciplines, such as social scientists and information systems researchers. Our research roadmap provides more than ten directions for future investigation.