Scenario-based Probing and Steering Cultural Values in Large Language Models
Abstract
AbstractEvaluation of cultural value alignment in Large Language Models (LLMs) typically relies on direct prompting with survey-style questions, which often elicit neutral or safety-aligned responses and fail to capture the model’s underlying cultural orientation. To overcome these challenges, we propose a framework for probing and steering latent cultural representations in LLMs along the two Inglehart–Welzel axes of the World Values Survey (WVS). By translating social value questions into scenario-based dilemmas, we extract token-level probabilities to measure implicit values and apply activation steering, optionally combined with country-conditioned prompting, to shift model behavior without retraining. Across three 4B-open-weight LLMs, four countries and three social domains, we find substantial variation in steerability. Importantly, we identify latent entanglement, where interventions along one Inglehart–Welzel axis induce a shift along the other. This entanglement is consistent with correlations present in human WVS data and persists across our experimental settings. Our work identifies empirical constraints on cultural alignment in LLMs.