EXPLAINING THE LINK BETWEEN CAUSAL REASONING AND EXPERT BEHAVIOR.

Abstract

Being able to provide the causal rationale that underlies a diagnosis or other medical decision is viewed by the authors as critical in providing satisfying explanations and justifications of that decision. Thus, expert systems are presented with a paradox. It appears that they should reason noncausally in most circumstances, but still have access to the causal rationale behind their decisions for providing explanations. They present a paradigm for expert system construction that provides that capability. In this approach, causal reasoning that is performed while the expert system is being designed does not appear in the expert system itself. However, because the design process is recorded in a machine readable form, explanation routines have access to that causal reasoning and thus can justify an expert system's behavior with a causal argument. The authors present three increasingly sophisticated frameworks that embody this approach: XPLAIN and two versions of the Explainable Expert Systems framework.