In-context bias propagation in LLM-based tabular data generation
Authors:
- Pol G. RecasensPRPol G. Recasens
- Alberto Gutierrez-TorreAGAlberto Gutierrez-Torre
- Jordi TorresJTJordi Torres
- Josep Ll. BerralJBJosep Ll. Berral
- Javier Carnerero-CanoJCJavier Carnerero-Cano
- Anisa HalimiAHAnisa Halimi
- Kieran FraserKFKieran Fraser
Open Access
- 1 November 2026
- journal article
- Published by Elsevier in Knowledge-Based Systems
- Vol. 355
Abstract
No abstract availableFunding Information
- Fundación Carmen y Severo Ochoa
- HORIZON EUROPE Framework Programme
- Agencia Estatal de Investigación
- Ministerio de Ciencia, Innovación y Universidades
- HORIZON EUROPE Framework Programme
- Departament d'Empresa i Coneixement, Generalitat de Catalunya
This publication has 12 references indexed in Scilit:
- Bias Mitigation in Large Language Models for Tabular Data ClassificationMachine Learning, 2026
- Fairness-preserving framework for machine learning: data bias quantification, model evaluation, and robustness across multiple datasetsAI and Ethics, 2025
- A novel approach for assessing fairness in deployed machine learning algorithmsScientific Reports, 2024
- Self-Diagnosis and Self-Debiasing: A Proposal for Reducing Corpus-Based Bias in NLPTransactions of the Association for Computational Linguistics, 2021
- A Survey on Bias and Fairness in Machine LearningACM Computing Surveys, 2021
- BOLD2021
- StereoSet: Measuring stereotypical bias in pretrained language models2021
- Queens are Powerful too: Mitigating Gender Bias in Dialogue Generation2020
- CrowS-Pairs: A Challenge Dataset for Measuring Social Biases in Masked Language Models2020
- SMOTE: Synthetic Minority Over-sampling TechniqueJournal of Artificial Intelligence Research, 2002