Understanding or Memorizing? A Case Study of German Definite Articles in Language Models

Documenti analoghi

• GRADIEND: Feature Learning within Neural Networks Exemplified through Biases
  di: Drechsel, Jonathan, et al.
  Pubblicazione: (2025)
• The GRADIEND Python Package: An End-to-End System for Gradient-Based Feature Learning
  di: Drechsel, Jonathan, et al.
  Pubblicazione: (2026)
• MAMUT: A Novel Framework for Modifying Mathematical Formulas for the Generation of Specialized Datasets for Language Model Training
  di: Drechsel, Jonathan, et al.
  Pubblicazione: (2025)
• Large Language Models can impersonate politicians and other public figures
  di: Herbold, Steffen, et al.
  Pubblicazione: (2024)
• Undesirable Memorization in Large Language Models: A Survey
  di: Satvaty, Ali, et al.
  Pubblicazione: (2024)