: Intelligent tutoring systems assist medical faculty in training and equipping students with the required clinical reasoning skills. Plausible student solutions to a given problem are rejected by tutoring systems as being incorrect, if they do not match a specific solution accepted by the tutoring system. This leads to brittleness in evaluating student solutions. In this paper we describe a combination of knowledge base expansion and exploitation of existing knowledge structure to enhance robustness in an intelligent tutoring system for medical problem-based learning using UMLS. We present a tutoring system that enriches the solution space by collating different plausible solutions and exploiting the knowledge structure in UMLS to offer students a broader scope of reasoning.