Gender biases in large language models
Abstract
This resource examines gender bias in large language models and how AI systems can reproduce and amplify existing social inequalities. It explores methods for detecting gender bias, the social implications of biased AI, and the role of open-source models in promoting transparency and accountability. Citation: Villarroya, Anna, Juan-José Boté-Vericad, Maddalena Fedele, Mari Vállez. 2026. Biaixos de gènere en els models de llenguatge externs. DOI: 10.5281/zenodo.18171512 Gender biases in large language models. Translation by: Anna Villarroya & Juan-José Boté-Vericad. DOI: 10.5281/zenodo.18188657
Fields of Study & Subjects
Computational and Text Analysis Methods
Text Readability and Simplification
Authorship Attribution and Profiling
Publication details
- Journal / source
- E-LIS Repository (University of Naples Federico II)
- Publication date
- 8 January 2026
- Language
- EN