ABSTRACT

Evaluating the occurrence and triggers of large language model (LLM) behaviorssuch as sycophancy, self-preference, or overconfidence– is critical for predicting realworld model deployment risks. However, existing situated behavioral evaluations typically ignore cultural context, limiting their generalizability across an increasingly global user base. To address this gap, we propose CuBEs– Culturally-situated Behavior Evaluations that probe for response patterns across diverse user countries. We first extend an automated testing pipeline to inject cultural context into behavioral test scenarios and subsequent evaluation. We assess the cultural adaptability of this pipeline by building a human-labeled dataset that captures nuanced dimensions of behavior understanding across 12 distinct cultures. Our dataset reveals significant cross-cultural variations that one-size-fits all approaches fail to capture. Through evaluating 13 open- and closedsource LLMs, we find that introducing cultural situatedness in the evaluation scenario creates significant variation in the presence of a behavior. For example, while our baseline experiments testing for political bias capture localized Western political dimensions like the American conservative-progressive divide, non-Western culturally situated evaluations surface entirely different axes of bias such as religious and colonial political issues. Our findings demonstrate that standard, culturally-agnostic evaluations fail to capture these shifts, highlighting the necessity of culturally situated behavioral testing for global deployments.