Exploring Large Language Models for Bias Mitigation and Fairness - IRIT - Université Toulouse III Paul Sabatier
Communication Dans Un Congrès Année : 2024

Exploring Large Language Models for Bias Mitigation and Fairness

Résumé

With the increasing integration of Artificial Intelli- gence (AI) in various applications, concerns about fairness and bias have become paramount. While numerous strategies have been proposed to miti- gate bias, there is a significant gap in the litera- ture regarding the use of Large Language Mod- els (LLMs) in these techniques. This paper aims to bridge this gap by presenting an innovative approach that incorporates LLMs for bias mitigation and ensuring fairness in AI systems. Our proposed method, built on previous research, is designed to be model and system-agnostic, while keeping humans in the loop. We envision these approaches to foster trust between AI developers and end-users/stakeholders, contributing to the discourse on responsible AI.
Fichier principal
Vignette du fichier
IJCAI_2024_AIGOV.pdf (1.95 Mo) Télécharger le fichier
Origine Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-04667517 , version 1 (05-08-2024)

Licence

Identifiants

  • HAL Id : hal-04667517 , version 1

Citer

Ibrahim Mohamed Serouis, Florence Sèdes. Exploring Large Language Models for Bias Mitigation and Fairness. International Joint Conference on Artificial Intelligence 2024 Workshop on AI Governance: Alignment, Morality, and Law, Aug 2024, Jeju Island, South Korea. ⟨hal-04667517⟩
169 Consultations
68 Téléchargements

Partager

More