The Root Shapes the Fruit: On the Persistence of Gender-Exclusive Harms in Aligned Language Models

Documenti analoghi

• A Differentiable Rank-Based Objective For Better Feature Learning
  di: Pavasovic, Krunoslav Lehman, et al.
  Pubblicazione: (2025)
• Beg to Differ: Understanding Reasoning-Answer Misalignment Across Languages
  di: Ovalle, Anaelia, et al.
  Pubblicazione: (2025)
• Classifier-Free Guidance: From High-Dimensional Analysis to Generalized Guidance Forms
  di: Pavasovic, Krunoslav Lehman, et al.
  Pubblicazione: (2025)
• Weisfeiler and Leman Go Measurement Modeling: Probing the Validity of the WL Test
  di: Subramonian, Arjun, et al.
  Pubblicazione: (2023)
• Tokenization Matters: Navigating Data-Scarce Tokenization for Gender Inclusive Language Technologies
  di: Ovalle, Anaelia, et al.
  Pubblicazione: (2023)