Explanations from intelligent systems: Theoretical foundations and implications for practice

Information systems with an "intelligent" or "knowledge" component are now prevalent and include knowledge-based systems, decision support systems, in telligent agents, and knowledge management systems. These systems are in pr inciple capable of explaining their reasoning or justifying their behavior. There appears to be a lack of understanding, however, of the benefits that can flow from explanation use, and how an explanation function should be c onstructed. Work with newer types of intelligent systems and help functions for everyday systems, such as word-processors, appears in many cases to ne glect lessons learned in the past. This paper attempts to rectify this situ ation by drawing together the considerable body of work on the nature and u se of explanations. Empirical studies, mainly with knowledge-based systems, are reviewed and linked To a sound theoretical base. The theoretical base combines a cognitive effort perspective, cognitive learning theory, and Tou lmin's model of argumentation. Conclusions drawn from the review have both practical and theoretical significance. Explanations are important to users in a number of circumstances-when the user perceives an anomaly, when they want to learn, or when they need a specific piece of knowledge to particip ate properly in problem solving. Explanations, when suitably designed, have been shown to improve performance and learning and result in more positive user perceptions of a system. The design is important, how ever, because i t appears that explanations will nor be used if the user has to exert "too much" effort to get them. Explanations should be provided automatically if this can be done relatively unobtrusively, or by hypertext links, and shoul d be context-specific rather than generic. Explanations that conform to Tou lmin's model of argumentation, in that they provide adequate justification for the knowledge offered, should be more persuasive and lead to greater tr ust, agreement, satisfaction, and acceptance-of the explanation and possibl y also of the system as a whole.