When AI Speaks, Whose Values Does It Express? A Cross-Cultural Audit of Individualism-Collectivism Bias in Large Language Models

Documenti analoghi

• Do Models Know Why They Changed Their Mind? Interpretability and Faithfulness of Chain-of-Thought Under Knowledge Conflict
  di: Venkata, Pruthvinath Jeripity
  Pubblicazione: (2026)
• Three Regimes of Context-Parametric Conflict: A Predictive Framework and Empirical Validation
  di: Venkata, Pruthvinath Jeripity
  Pubblicazione: (2026)
• Reinforcement Learning from Human Feedback: Whose Culture, Whose Values, Whose Perspectives?
  di: Barman, Kristian González, et al.
  Pubblicazione: (2024)
• Whose Morality Do They Speak? Unraveling Cultural Bias in Multilingual Language Models
  di: Aksoy, Meltem
  Pubblicazione: (2024)
• Cross-Language Bias Examination in Large Language Models
  di: Liang, Yuxuan, et al.
  Pubblicazione: (2025)