Localized Cultural Knowledge is Conserved and Controllable in Large Language Models

Documenti analoghi

• Do Llamas Work in English? On the Latent Language of Multilingual Transformers
  di: Wendler, Chris, et al.
  Pubblicazione: (2024)
• Separating Tongue from Thought: Activation Patching Reveals Language-Agnostic Concept Representations in Transformers
  di: Dumas, Clément, et al.
  Pubblicazione: (2024)
• What is a Number, That a Large Language Model May Know It?
  di: Marjieh, Raja, et al.
  Pubblicazione: (2025)
• Identifying and Mitigating the Influence of the Prior Distribution in Large Language Models
  di: Zhang, Liyi, et al.
  Pubblicazione: (2025)
• CORE-Bench: Fostering the Credibility of Published Research Through a Computational Reproducibility Agent Benchmark
  di: Siegel, Zachary S., et al.
  Pubblicazione: (2024)