The Male Abstraction Bias in Internet Culture and Large Language Models

Abstract:Two foundational aspects of human cognition, abstractness and gender, are typically examined as separable. Here, we find they are systematically linked throughout the entire space of concepts spanning single (N = 40,000) and multi-word expressions (N = 67,000): across billions of words and millions of images on the internet -- and across numerous measurement techniques -- more abstract concepts are more associated with men, an effect which replicates in languages around the world. This pattern not only holds across conceptual domains, but it also maps onto grammatical structure: verbs and adverbs are more abstract and more male-coded, a system-wide trace of stereotypes accentuating agentic qualities in men. Furthermore, this bias emerges in human and AI responses in free association tasks, indicating its internalization and its algorithmic reproduction. The male abstraction bias may underlie and unify a range of stereotypes, evidencing gender as a core organizing dimension in conceptual space.

Computers and Society (cs.CY); Computation and Language (cs.CL); Human-Computer Interaction (cs.HC)

arXiv:2611.05730 [cs.CY]

(or arXiv:2611.05730v1 [cs.CY] for this version)

https://doi.org/10.48550/arXiv.2611.05730 Focus to learn more arXiv-issued DOI via DataCite (pending registration)

arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.

Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.

Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.