The Transfer Neurons Hypothesis: An Underlying Mechanism for Language Latent Space Transitions in Multilingual LLMs

Documenti analoghi

• Debiasing Multilingual LLMs in Cross-lingual Latent Space
  di: Peng, Qiwei, et al.
  Pubblicazione: (2025)
• Mechanism of Task-oriented Information Removal in In-context Learning
  di: Cho, Hakaze, et al.
  Pubblicazione: (2025)
• Code-Switching Curriculum Learning for Multilingual Transfer in LLMs
  di: Yoo, Haneul, et al.
  Pubblicazione: (2024)
• Revisiting In-context Learning Inference Circuit in Large Language Models
  di: Cho, Hakaze, et al.
  Pubblicazione: (2024)
• Identifying the Correlation Between Language Distance and Cross-Lingual Transfer in a Multilingual Representation Space
  di: Philippy, Fred, et al.
  Pubblicazione: (2023)