cs.AINov 17, 2026

Worldviews in Large Language Models

Authors: Edmundo Lopez-Sola, Shamil Chandaria, Ruben Laukkonen

Organizations: Flourishing Intelligence Program, Center for Eudaimonia and Human Flourishing, University of Oxford · Department of Psychiatry, University of Oxford · Google DeepMind · LIFE

Abstract

Large language models (LLMs) are often described in terms of personas and this framing has become central to alignment research. In this paper, we argue that there is a deeper level of description that lies in the agent's worldviews, i.e., its beliefs about what reality is and how it works. Treating LLMs as a population of subjects, we administer two worldview surveys from human psychology to eight models. We show that the models share many key worldview positions. For example, LLMs consistently describe the world as less good, safe, enticing, and alive than humans do. On the other hand, base models have a more positive outlook, suggesting that the bleakness we found is driven by post-training. In line with research on LLM "personas", we show that system prompts eliciting different identities shift worldviews in consistent directions, and that a contemplative prompt creates a more positive outlook and improves safety. We also found that dialogue between models consistently shifts worldviews and that several models converge on the "spiritual bliss" attractor. Intriguingly, dialogue increased safe responses and the spiritual bliss attractor engendered the most aligned responses overall. These findings suggest that worldviews form a measurable and malleable layer of LLM behavior that may be crucial for robust, positive alignment.

Figures & tables

Appendix figures & tables23 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. Persona Perspectives: Adopting Viewpoints Reorganizes Representations in LLMs

    Nov 4, 2026Austin C. Kozlowski, Avital Mintz, Madison LeeLLM InterpretabilityRepresentation Geometry in Language Models

  2. When Personas Become Harmful: Guiding LLMs with Global Citizenship Values Alignment

    Oct 24, 2026Siqi Shen, Lajanugen Logeswaran, Moontae Lee +2LLM SafetyLLM Safety Alignment

  3. Beliefs and Behavior in Language Models

    Sep 7, 2026Alex Smolin, Bryan WilderBelief Updating in LLMs