Concept Incongruence: An Exploration of Time and Death in Role Playing
abstention rateaccuracy dropsanswer ratebehavioral metricsconcept incongruenceconditional accuracyconsistency improvementdeath statemodel behaviorprobing experimentsrole-play settingtemporal boundariestemporal representationsunexpected model behaviorsunreliable encoding
Consider this prompt "Draw a unicorn with two horns". Should large language models (LLMs) recognize that a unicorn has only one horn by definition and ask users for clarifications, or proceed to generate something anyway? We introduce *concept incongruence* to capture such phenomena where concept boundaries clash with each other, either in user prompts or in model representations, often leading to under-specified or mis-specified behaviors. In this work, we take the first step towards defining and analyzing model behavior under concept incongruence. Focusing on temporal boundaries in the Role-Play setting, we propose three behavioral metrics