Clustering Discourses: Racial Biases in Short Stories about Women Generated by Large Language Models
Not on the map. Why?
Abstract (arXiv)
This study investigates how large language models, in particular LLaMA 3.2-3B, construct narratives about Black and white women in short stories generated in Portuguese. From 2100 texts, we applied computational methods to group semantically similar stories, allowing a selection for qualitative analysis. Three main discursive representations emerge: social overcoming, ancestral mythification and subjective self-realization. The analysis uncovers how grammatically coherent, seemingly neutral texts materialize a crystallized, colonially structured framing of the female body, reinforcing historical inequalities. The study proposes an integrated approach, that combines machine learning techniques with qualitative, manual discourse analysis.
Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 10 of its 29 references that are in the map. First posted on arXiv 2 Sep 2025.
Builds on
10 of 29 references.
References · 10
- 2024The Llama 3 Herd of Modelscited by 14,715
- 2024M3-Embedding: Multi-Linguality, Multi-Functionality, Multi-Granularity Text Embeddings Through Self-Knowledge Distillationcited by 1,073
- 2020Language (Technology) is Power: A Critical Survey of "Bias" in NLPcited by 956
- 2019The Woman Worked as a Babysitter: On Biases in Language Generationcited by 541
- 2019On Measuring Social Biases in Sentence Encoderscited by 398
- 2021Persistent Anti-Muslim Bias in Large Language Modelscited by 377
- 2019Identifying and Reducing Gender Bias in Word-Level Language Modelscited by 214
- 2024What's in a Name? Auditing Large Language Models for Race and Gender Biascited by 51
- 2023Nationality Bias in Text Generationcited by 50
- 2025Yet another algorithmic bias: A Discursive Analysis of Large Language Models Reinforcing Dominant Discourses on Gender and Racecited by 1
Built on by
Not cited yet.