Understanding or Memorizing? A Case Study of German Definite Articles in Language Models Paper • 2601.09313 • Published 5 days ago
MAMUT: A Novel Framework for Modifying Mathematical Formulas for the Generation of Specialized Datasets for Language Model Training Paper • 2502.20855 • Published Feb 28, 2025
GRADIEND: Monosemantic Feature Learning within Neural Networks Applied to Gender Debiasing of Transformer Models Paper • 2502.01406 • Published Feb 3, 2025