Comparative Analysis of Clustering and Projection Debiasing Methods for Gender Bias in Contextualized Embeddings

Taking an interdisciplinary approach to surveying issues around gender bias in textual and visual AI, we present literature on gender bias detection and mitigation in NLP, CV, as well as combined visual-linguistic models. We identify conceptual parallels between these strands of research as well as how methodologies were adapted cross-disciplinary from NLP to CV. We also find that there is a growing awareness for theoretical frameworks from the social sciences around gender in NLP that could be beneficial for aligning bias analytics in CV with human values and conceptualising gender beyond the

Research goal: Do clustering-based debiasing methods for contextualized embeddings demonstrate better downstream task performance on gender-bias benchmarks like WinoBias or CrowS-Pairs compared to projection-based methods?

Autonomous synthesis report generated by SOVEREIGN Research Kernel. Tribunal consensus score: 8.0/10.