Logic-Based Explainability: Past, Present & Future

TL;DR

This paper provides a comprehensive survey of logic-based explainability in AI, emphasizing its importance for trustworthy decision-making and highlighting recent research, misconceptions, and future directions in the field.

Contribution

It offers a detailed overview of the origins, current state, and future prospects of logic-based XAI, clarifying misconceptions and emphasizing its rigor compared to other approaches.

Findings

Logic-based XAI is a rigorous alternative to non-rigorous methods.

Current research explores new logical frameworks for explainability.

Myths about non-rigorous XAI approaches are critically addressed.

Abstract

In recent years, the impact of machine learning (ML) and artificial intelligence (AI) in society has been absolutely remarkable. This impact is expected to continue in the foreseeable future. However,the adoption of AI/ML is also a cause of grave concern. The operation of the most advances AI/ML models is often beyond the grasp of human decision makers. As a result, decisions that impact humans may not be understood and may lack rigorous validation. Explainable AI (XAI) is concerned with providing human decision-makers with understandable explanations for the predictions made by ML models. As a result, XAI is a cornerstone of trustworthy AI. Despite its strategic importance, most work on XAI lacks rigor, and so its use in high-risk or safety-critical domains serves to foster distrust instead of contributing to build much-needed trust. Logic-based XAI has recently emerged as a rigorous alternative to those other non-rigorous methods of XAI. This paper provides a technical survey of logic-based XAI, its origins, the current topics of research, and emerging future topics of research. The paper also highlights the many myths that pervade non-rigorous approaches for XAI.