Based on billions of words on the internet, people = men

By April H. Bailey, Adina Williams, Andrei Cimpian. 2022

69 citations recorded by the source corpus.

Recent advances have made it possible to precisely measure the extent to which any two words are used in similar contexts. In turn, this measure of similarity in linguistic context also captures the extent to which the concepts being denoted are similar. When extracted from massive corpora of text written by millions of individuals, this measure of linguistic similarity can provide insight into the collective concepts of a linguistic community, concepts that both reflect and reinforce widespread ways of thinking. Using this approach, we investigated the collective concept person/people, which forms the basis for nearly all societal decision- and policy-making. In three studies and three preregistered replications with similarity metrics extracted from a corpus of over 630 billion English words, we found that the collective concept person/people is not gender-neutral but rather prioritizes men over women—a fundamental bias in our species’ collective view of itself.

Subfields: Artificial Intelligence, Communication, Natural Language Processing

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Communication

In Natural Language Processing

Citations in the corpus

Llama 2: Open Foundation and Fine-Tuned Chat Models (2023, background): “For instance, Bailey et al. (2022) shows that in massive text corpora, words representing “people” are often used in more similar contexts to words representing “men” than to words representing “women,” and Ganesh et al. (2023) demonstrates that a model’s performance on fairness metrics can be…”
Perturbation Augmentation for Fairer NLP (2022, background): “If it were throats , we might conclude that they is morphologically plural and refers to multiple people of mixed, unknown, or known non-binary gender. a discussion of the complexity of relevant pragmatic factors, and Bailey et al. 2022 for a gender-related example.”
A Survey on Large Language Model (LLM) Security and Privacy: The Good, the Bad, and the Ugly (2023, background): “Wesley Tann et al. [261] focused on the evaluation of LLMs in the context of cybersecurity Capture-The-Flag (CTF) exercises (participants find “flags” by exploiting system vulnerabilities).”