An XAI View on Explainable ASP: Methods, Systems, and Perspectives

This arXiv survey examines explainable AI (XAI) methods applied to Answer Set Programming (ASP), a symbolic AI approach used for declarative reasoning. The paper catalogs existing explanation approaches and tools while identifying gaps in coverage across different user scenarios, establishing a foundation for future XAI research in logic-based systems.

Answer Set Programming represents a cornerstone of symbolic AI, enabling rule-based reasoning that contrasts sharply with the black-box nature of modern machine learning. This survey bridges the growing gap between ASP's inherent interpretability and the formal XAI framework increasingly demanded by regulators and practitioners. The timing is significant: as enterprises deploy AI systems in high-stakes domains like healthcare, finance, and autonomous systems, the ability to explain reasoning becomes critical for compliance and trust.

The symbolic AI renaissance has gained momentum as organizations recognize limitations in purely neural approaches. ASP's declarative nature—where programmers specify rules rather than train weights—already provides better interpretability than deep learning. However, this survey reveals that existing ASP explanation tools address disparate use cases inconsistently. Different users ask different questions: some need justifications for specific conclusions, others need contrastive explanations (why A instead of B), and still others require debugging of rule interactions.

For the AI industry, this work validates demand for explainability research in logic-based systems. The gap analysis points to unmet needs in areas like interactive explanation generation, temporal reasoning explanations, and user-centered evaluation frameworks. Developers building AI systems in regulated sectors may benefit from ASP's formal reasoning capabilities once explanation tooling matures. The research direction suggests a shift toward hybrid systems combining symbolic reasoning with neural components, where ASP handles explainable decision pathways.

Industry observers should watch for standardized explanation interfaces emerging from this research, which could accelerate ASP adoption in enterprise contexts where explainability is non-negotiable.

• →ASP's rule-based formalism provides inherent interpretability advantages over neural approaches for explainable AI applications.
• →Current ASP explanation tools address specific scenarios inconsistently, leaving gaps in coverage for diverse user needs.
• →The survey identifies research directions including interactive explanations, temporal reasoning support, and standardized evaluation frameworks.
• →Hybrid systems combining ASP's symbolic reasoning with neural components may emerge as a practical solution for regulated industries.
• →Formal explanation methods for logic-based systems could accelerate adoption in high-stakes domains requiring transparent decision-making.