world-values-survey

Tag

Cards List
#world-values-survey

Personalization, Personas, and Forecasting in Value Alignment

arXiv cs.AI · 2d ago Cached

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.

0 favorites 0 likes
#world-values-survey

Scenario-based Probing and Steering Cultural Values in Large Language Models--Extended Version

arXiv cs.CL · 2026-06-11 Cached

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.

0 favorites 0 likes
#world-values-survey

Beyond Alignment: Value Diversity as a Collective Property in Multicultural Agent Systems

Hugging Face Daily Papers · 2026-06-04 Cached

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.

0 favorites 0 likes
#world-values-survey

Parametric Social Identity Injection and Diversification in Public Opinion Simulation

Hugging Face Daily Papers · 2026-06-01 Cached

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.

0 favorites 0 likes
#world-values-survey

Cultural Value Alignment Via Latent Activation Steering in Large Language Models

arXiv cs.CL · 2026-05-27 Cached

A framework for evaluating and steering cultural values in LLMs using scenario-based behavioral probing and activation steering, revealing latent entanglement of value dimensions.

0 favorites 0 likes
← Back to home

Submit Feedback