Login
Dataset-level societal bias mitigation with text-to-image model
Systems and methods are used to mitigate societal bias in image-text datasets by removing spurious correlations between protected groups and image attributes. Using text-guided inpainting models, the methods ensures protected group independence from all attributes and mitigates inpainting biases through data filtering. Evaluations on multi-label image classification and image captioning tasks show that the methods effectively reduce bias without compromising performance across various models.
2025
Interventions to Mitigate COVID-19 Misinformation: A Systematic Review and Meta-Analysis
Journal of Health Communication
2021
26
12
846-857
KI-Agenten zwischen Kontrolle und Subjektivierung: Zur Produktion neuer Machtverhältnisse
Workshop Handeln, Wissen und Macht in Mensch-Maschine- Interaktionen
2025
Ethical Considerations for Responsible Data Curation
Advances in Neural Information Processing Systems 36 (NeurIPS 2023)
2023
36
55320-55360
Social media as classification systems: procedural normative choices in user profiling
Handbook of Critical Studies of Artificial Intelligence
Edward Elgar Publishing
2023
Augmented Datasheets for Speech Datasets and Ethical Decision-Making
881-904
2023 ACM Conference on Fairness Accountability and Transparency
Association for Computing Machinery (ACM)
2023