Exploring Fairness and Bias Mitigation in Large Language Models

Jaidi, Charan Reddy (2025) Exploring Fairness and Bias Mitigation in Large Language Models. Masters thesis, Dublin, National College of Ireland.

Preview	PDF (Master of Science) Download (1MB) | Preview
Preview	PDF (Configuration Manual) Download (725kB) | Preview

Abstract

Large Language Models (LLMs) such as GPT-2 have achieved remarkable success in natural language processing but are increasingly criticised for exhibiting social biases that can reinforce stereotypes and perpetuate inequality. This study systematically evaluates GPT-2’s bias and toxicity using two benchmark datasets: CrowS-Pairs (measuring stereotype preference) and RealToxicityPrompts (measuring toxicity in generated text). We implement a lightweight mitigation strategy combining Counterfactual Data Augmentation (CDA) with Low-Rank Adaptation (LoRA) fine-tuning and compare pre- and post-mitigation results. Baseline experiments show an overall CrowS-Pairs stereotype preference rate of 0.5736 and a mean toxicity score of 0.1106. CDA+LoRA yields modest reductions in bias for some categories while maintaining model utility. The findings underscore that although targeted mitigations can address specific bias dimensions, achieving broad fairness in LLMs remains an open challenge, requiring multi-faceted strategies and lifecycle-wide interventions.

Item Type:	Thesis (Masters)
Supervisors:	Name Email Hamill, David UNSPECIFIED
Subjects:	Q Science > QH Natural history > QH301 Biology > Methods of research. Technique. Experimental biology > Data processing. Bioinformatics > Artificial intelligence Q Science > Q Science (General) > Self-organizing systems. Conscious automata > Artificial intelligence P Language and Literature > P Philology. Linguistics > Computational linguistics. Natural language processing
Divisions:	School of Computing > Master of Science in Data Analytics
Depositing User:	Ciara O'Brien
Date Deposited:	25 Aug 2026 14:50
Last Modified:	25 Aug 2026 14:50
URI:	https://norma.ncirl.ie/id/eprint/9632

Actions (login required)

View Item