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

Rule-based systems offer natural explainability: Answer Set Programming's rule-based formalism is "inherently attractive for explainable and interpretive reasoning," making it a promising approach for AI systems that need to justify their decisions to users in understandable terms.

Current explanation tools have significant gaps: The survey identifies that existing ASP explanation approaches "often tackle specific explanatory settings and may not cover all scenarios that ASP users encounter," meaning no single tool comprehensively addresses all user needs for understanding AI reasoning.

Different users need different types of explanations: The paper emphasizes that explanations must be connected to "user questions for explanation," suggesting that effective AI transparency requires tailoring explanations to what specific stakeholders actually want to know rather than providing one-size-fits-all answers.

Symbolic AI deserves more XAI attention: By surveying explanation methods for ASP specifically, the paper highlights that explainability research has often focused on other AI approaches, leaving symbolic reasoning systems—which are inherently more interpretable—underexplored in the XAI literature.

Future work needed to close explanation gaps: The authors "pinpoint gaps in existing ASP explanation approaches and identify research directions for future work," indicating that developing more comprehensive explanation methods for rule-based systems is an important next step for responsible AI deployment.