arXiv cs.CY· Douglas Guilbeault, Bhargav Srinivasa Desikan·· 11 小时前AI 评分45
互联网文化与大型语言模型中的男性抽象偏差
The Male Abstraction Bias in Internet Culture and Large Language Models
AI 导读
研究分析互联网数十亿词与数百万张图像及 4 万个单词、6.7 万个多词表达发现，越抽象的概念越与男性关联，该效应在全球多种语言中均可复现。这一偏差还映射到语法结构：动词和副词更抽象也更偏男性编码，并在人类与 AI 的自由联想任务中同时出现，表明其已被模型内化并算法性再现。
正文 · 原文
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.
| Subjects: | Computers and Society (cs.CY); Computation and Language (cs.CL); Human-Computer Interaction (cs.HC) |
| Cite as: | arXiv:2611.05730 [cs.CY] |
| (or arXiv:2611.05730v1 [cs.CY] for this version) | |
| https://doi.org/10.48550/arXiv.2611.05730 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Bhargav Srinivasa Desikan [view email]
[v1]
Tue, 3 Nov 2026 23:02:00 UTC (7,701 KB)
来源：arXiv cs.CY · arxiv.org