Answering the "why" in Answer Set Programming - A Survey of Explanation Approaches

TL;DR

This survey reviews various explanation methods in Answer Set Programming (ASP), focusing on understanding why certain solutions are derived or not, which is crucial for AI transparency and compliance with regulations.

Contribution

It provides a comprehensive overview of existing explanation approaches in ASP, comparing their methodologies and highlighting their relevance for AI transparency and regulation compliance.

Findings

Overview of explanation techniques like off-line justifications and causal graphs

Comparison of methods explaining answer set solutions and non-solutions

Discussion on the importance of explanations for AI regulation compliance

Abstract

Artificial Intelligence (AI) approaches to problem-solving and decision-making are becoming more and more complex, leading to a decrease in the understandability of solutions. The European Union's new General Data Protection Regulation tries to tackle this problem by stipulating a "right to explanation" for decisions made by AI systems. One of the AI paradigms that may be affected by this new regulation is Answer Set Programming (ASP). Thanks to the emergence of efficient solvers, ASP has recently been used for problem-solving in a variety of domains, including medicine, cryptography, and biology. To ensure the successful application of ASP as a problem-solving paradigm in the future, explanations of ASP solutions are crucial. In this survey, we give an overview of approaches that provide an answer to the question of why an answer set is a solution to a given problem, notably off-line justifications, causal graphs, argumentative explanations and why-not provenance, and highlight their similarities and differences. Moreover, we review methods explaining why a set of literals is not an answer set or why no solution exists at all.