Granular Feedback: Leveraging Domain Expertise and Explainable AI to Effectively Steer Models

sponsorship: We would like to thank ZAVO, and Joke Vandepitte in particular, for allowing us to collaborate. We would like to thank FWO by facilitating this interdisciplinary research. Additionally, we would like to thank all participants for their time and valuable insights. This research is part of the research projects funded by KU Leuven (grant C14/21/072) and the Flanders AI Research Program (FAIR). (KU Leuven|C14/21/072, Flanders AI Research Program (FAIR))