cs.CYNov 3, 2026

The Male Abstraction Bias in Internet Culture and Large Language Models

Authors: Douglas Guilbeault, Bhargav Srinivasa Desikan

Organizations: Stanford University, Stanford, CA, USA · Oxford Internet Institute, Oxford, UK

Abstract

Conceptual abstraction and gender are two equally central aspects of the human mind, yet they have traditionally been studied in isolation from one another, as though they were fundamentally separate. Here, we find gender and abstraction are systematically linked throughout the 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, including human and AI classifications --- more abstract concepts are more associated with men, a pattern we show replicates in languages around the world. This male abstraction bias not only holds across semantic domains, but it also maps onto grammatical structure: verbs and adverbs are more abstract and more male-coded, revealing a system-wide trace of stereotypes accentuating agentic qualities in men. Furthermore, we show this bias readily emerges in the free associations humans and AIs produce in controlled online tasks, indicating its psychological internalization and its algorithmic reproduction. These findings identify a latent structure in conceptual space that unifies a range of stereotypes: for example, framings of women as more embodied, emotional, and warm, versus men as more cognitive, rational, and competent; as well as erroneous views of men as better at mathematics, science, and engineering. More broadly, by analyzing an unprecedentedly large, multimodal sample of online data, we provide culture-wide evidence of gender as a core organizing principle shaping conceptual space far beyond the characterization of people and social roles.

Figures & tables

Explore similar work

Oct 20, 2026

Guilt by Association: Semantic Leakage Drives Associative Gender Bias

Semantic leakage occurs when a concept in the prompt steers model generation about an entity, even though the concept is irrelevant to it (e.g., a person who likes yellow is said to work as a school bus driver). It has mostly been studied in settings where the concept is directly attributed to the entity the model is asked about. This leaves open whether leakage is a flawed heuristic, where the model builds a profile of that entity, or a much broader associative tendency, e.g., working across seemingly unrelated entities. We argue for the latter: even after removing the attribution of the concept to the specific entity, leakage persists. Next, we extend this idea to gender bias. While work on gender bias in LMs typically looks at cases where the stereotyped concept is attributed to an entity, our findings suggest that a concept may steer outputs with its mere presence in the scene. We show this using gendered concepts under two conditions: when the subject engages with the concept, and when the concept just sits in the scene. We find that both shift model generation toward the stereotype to a similar extent. Together, our results suggest that semantic leakage drives a form of bias that is overlooked by current evaluations.
Nov 13, 2026

Evaluating Human Sensitivity to Gender Biased AI-Generated Content through Human Assessment of Google's Autocomplete Function

Large Language Models (LLMs) are increasingly present, but their effects on human users remain underexplored. We tested whether AI-attributed information influences views regarding gender-related statements, a domain where biases are pervasive. Spanish-speaking participants recruited through Prolific evaluated biased statements derived from Google's autocomplete function and human-authored, non-biased gender-related facts. Participants were either informed that some of the material was AI-generated or received no information about its origin. AI attribution did not affect reaction times or agreement judgments. This result suggests that AI-generated content does not automatically raise credibility concerns and may be evaluated with less scrutiny compared to human-produced content.
May 29, 2026

Anchoring LLM Gender Bias to Human Baselines: A Cross-Lingual Audit

We audit six large language models (LLMs) for gender stereotyping across English, Korean, Chinese, and Japanese. Three were developed primarily for English-language use (Claude, GPT, Gemini) and three for East Asian use (DeepSeek, Syn-Pro, HyperCLOVA X). We adopt the HEXACO-100 personality inventory and anchor each model against a cross-cultural human dataset spanning 48 countries to ask not whether LLMs are biased, but how far their gender attributions drift from the populations they are deployed among. Our findings show that their stereotyping spans a range roughly 2.5 times wider than the entire cross-country range found in humans, and the effect can compound across languages. One English-centric model, prompted in Korean, reached 5 times the local baseline, even when the prompt stated the candidate had already been hired, which often dampens human stereotyping. To characterize such behaviors without ranking them, we introduce a four-pattern framework -- concordance, suppression, reorganization, and amplification -- across 24 (model x language) cells. Item-level analysis reveals that translation does not just rescale stereotypes, but changes the attributes tied to it, hiding significant rearrangement under the surface while appearing well-calibrated. Our results ultimately suggest that no single debiasing pipeline is likely to address bias evenly across linguistic boundaries.