Analyzing Cognitive Differences Among Large Language Models through the Lens of Social Worldview
This work addresses the need for more transparent and socially responsible language technologies by uncovering implicit biases in LLMs, which is important for developers and users concerned with ethical AI, though it is incremental in building on existing bias research.
The paper tackled the problem of understanding how large language models (LLMs) form and express socio-cognitive worldviews, such as attitudes toward authority and equality, by introducing the Social Worldview Taxonomy (SWT) and applying it to 28 diverse LLMs, revealing distinct cognitive profiles and showing that social cues systematically shape these attitudes.
Large Language Models (LLMs) have become integral to daily life, widely adopted in communication, decision-making, and information retrieval, raising critical questions about how these systems implicitly form and express socio-cognitive attitudes or "worldviews". While existing research extensively addresses demographic and ethical biases, broader dimensions-such as attitudes toward authority, equality, autonomy, and fate-remain under-explored. In this paper, we introduce the Social Worldview Taxonomy (SWT), a structured framework grounded in Cultural Theory, operationalizing four canonical worldviews (Hierarchy, Egalitarianism, Individualism, Fatalism) into measurable sub-dimensions. Using SWT, we empirically identify distinct and interpretable cognitive profiles across 28 diverse LLMs. Further, inspired by Social Referencing Theory, we experimentally demonstrate that explicit social cues systematically shape these cognitive attitudes, revealing both general response patterns and nuanced model-specific variations. Our findings enhance the interpretability of LLMs by revealing implicit socio-cognitive biases and their responsiveness to social feedback, thus guiding the development of more transparent and socially responsible language technologies.