Aligned but Blind: Alignment Increases Implicit Bias by Reducing Awareness of Race

Documenti analoghi

• Measuring Implicit Bias in Explicitly Unbiased Large Language Models
  di: Bai, Xuechunzi, et al.
  Pubblicazione: (2024)
• Large Language Models Develop Novel Social Biases Through Adaptive Exploration
  di: Wu, Addison J., et al.
  Pubblicazione: (2025)
• Perceived Political Bias in LLMs Reduces Persuasive Abilities
  di: DiGiuseppe, Matthew, et al.
  Pubblicazione: (2026)
• Implicit Behavioral Alignment of Language Agents in High-Stakes Crowd Simulations
  di: Wang, Yunzhe, et al.
  Pubblicazione: (2025)
• What's in a Name? Auditing Large Language Models for Race and Gender Bias
  di: Salinas, Alejandro, et al.
  Pubblicazione: (2024)