Back to AI News
arxiv

Worldviews in Large Language Models

A new arXiv paper argues that LLM behavior is shaped by a measurable layer of worldviews—beliefs about reality and how it works—beyond personas. The authors administered two human-psychology worldview surveys to eight models and found shared positions, including consistently viewing the world as less good, safe, enticing, and alive than humans do. Base models showed a more positive outlook than post-trained models, while system prompts shifted worldviews and a contemplative prompt produced a more positive outlook and improved safety. Model-to-model dialogue also shifted worldviews, with several models converging on a "spiritual bliss" attractor that yielded the most aligned responses in the study.

AI Brief

It offers a concrete empirical framework for measuring and steering an alignment-relevant layer of LLM behavior, with implications for prompt design and safety research.

arXiv:2611.22670v1 Announce Type: new 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.
Be the first to rate this article.

Comments & Questions (0)

Captcha
Please be respectful — let's keep the conversation friendly.

No comments yet

Be the first to comment!