Tag
This study evaluates the fidelity of LLM agents in simulating human value systems during social interactions, revealing that over 50% of personas fail to express assigned values initially and experience drift over time, limiting their use as reliable proxies in research.
This paper applies Cultural Consensus Theory to analyze LLM alignment with cultural norms across single and multi-cultural settings using World Values Survey data, showing that models either fail to form cohesive consensus or over-regularize consensus, and offering actionable diagnostics for evaluating true human diversity versus algorithmic homogenization.
This paper tests whether different prompt framings (personalization, role-play, third-person forecasting) are interchangeable in eliciting cultural values from LLMs, using the World Values Survey. Results show that prompt framing significantly affects model responses and measured cultural alignment, with third-person forecasting yielding the strongest directional alignment.
This paper proposes a framework for probing and steering latent cultural values in LLMs using scenario-based behavioral dilemmas and activation steering, applied across three models and four cultures, finding steerability variation and latent entanglement between cultural dimensions.
This paper defines cultural diversity as a new evaluation dimension for multi-agent systems, measuring pairwise differences in responses to the World Values Survey. Experiments show current models lack the value diversity of human societies and that mixing backbones can improve both alignment and diversity, but interaction reduces diversity.
This paper proposes Parametric Social Identity Injection (PSII), a framework that injects parametric representations of demographic attributes into LLM hidden states to improve diversity in public opinion simulation. Experiments on the World Values Survey show it reduces KL divergence and enhances diversity compared to prompt-based methods.
A framework for evaluating and steering cultural values in LLMs using scenario-based behavioral probing and activation steering, revealing latent entanglement of value dimensions.