Research Proposal - A Future Only 'Generated' for Some: an Investigation into the Gender Bias in Generative AI Models Fine-tuned on Stereotyped or Sexist Datasets
My project explores gender bias in generative AI (textual and visual generation) and investigates whether fine-tuning with equity-focused datasets can reduce such bias. It also aims to develop a framework consisting of scales and metrics for evaluating gender fairness in AI-generated outputs.
Preview
Recommended Content
Social Sciences, Scholars' Stories, Research, Durham University, University College London, University of Leeds, University of St Andrews, University of York, Leadership & Research Laidlaw Scholars, Alumni, Opportunities, University of Cambridge, London School of Economics and Political Science, Imperial College London, University of Oxford - SDG Impact Lab
Please sign in
If you are a registered user on Laidlaw Scholars Network, please sign in