Logo Lanfrica
  • Accueil
  • Atlas
  • Analyses
  • Documentation
  • Sign in

© 2026 Lanfrica. Tous droits réservés. Tous les droits d'auteur des ressources affichées sur le site Web Lanfrica appartiennent aux détenteurs de droits d'auteur d'origine, sauf indication contraire explicite.

Evaluating Racial Bias in Large Language Models: The Necessity for "SMOKY"

Domaine:

natural language processing

Type de record:

paper
Créateur:
IJSC
Éditeur:
Zenodo
Hôte:avatar

This paper evaluates the understanding and biases of large language models (LLMs) regarding racism by comparing their responses to those of prominent African-centered scholar, Dr. Frances Cress Welsing. The study identifies racial biases in LLMs, illustrating the critical need for specialized AI systems like "Smoky,"[1] designed to address systemic racism with a foundation in African-centered scholarship. By highlighting disparities and potential biases in LLM responses, the research aims to contribute to the development of more culturally aware and contextually sensitive AI systems. This comparative analysis underscores the necessity for integrating African-centered perspectives in AI development to dismantle white supremacy and promote social justice.

Visit

doi.org

Licenses

info:eu-repo/semantics/openAccessCreative Commons Attribution 4.0 Internationalhttps://creativecommons.org/licenses/by/4.0/legalcode

Similaires

AfriStereo: A Culturally Grounded Dataset for Evaluating Stereotypical Bias in Large Language ModelsSociolinguistic Bias and Language Inequality in Large Language ModelsAraRegBias: Evaluating Dialectal and Stereotypical Bias in Arabic Large Language Models via Multi-Component MetricsInvestigating Bias in Bulgarian in the Context of Large Language ModelsEvaluating the Capabilities of Large Language Models for Multi-label Emotion UnderstandingEvaluating Metalinguistic Knowledge in Large Language Models across the World's Languages

AfriStereo: A Culturally Grounded Dataset for Evaluating Stereotypical Bias in Large Language Models

Existing AI bias evaluation benchmarks largely reflect Western perspectives, leaving African context

Sociolinguistic Bias and Language Inequality in Large Language Models

Large language models (LLMs) are increasingly deployed across multilingual applications, yet persist

AraRegBias: Evaluating Dialectal and Stereotypical Bias in Arabic Large Language Models via Multi-Component Metrics

Abstract Large Language Models (LLMs) have achieved strong multilingual capabiliti

Investigating Bias in Bulgarian in the Context of Large Language Models

Abstract This paper investigates the detection and annotation of bias in Bulgarian

Evaluating the Capabilities of Large Language Models for Multi-label Emotion Understanding

Large Language Models (LLMs) show promising learning and reasoning abilities. Compared to other NLP

Evaluating Metalinguistic Knowledge in Large Language Models across the World's Languages

LLMs are routinely evaluated on language use, yet their explicit knowledge about linguistic structur