Knowledge Localization in Mixture-of-Experts LLMs Using Cross-Lingual Inconsistency

Documenti analoghi

• Large Reasoning Models Struggle to Transfer Parametric Knowledge Across Scripts
  di: Bandarkar, Lucas, et al.
  Pubblicazione: (2026)
• The Unreasonable Effectiveness of Model Merging for Cross-Lingual Transfer in LLMs
  di: Bandarkar, Lucas, et al.
  Pubblicazione: (2025)
• Multilingual Routing in Mixture-of-Experts
  di: Bandarkar, Lucas, et al.
  Pubblicazione: (2025)
• Layer Swapping for Zero-Shot Cross-Lingual Transfer in Large Language Models
  di: Bandarkar, Lucas, et al.
  Pubblicazione: (2024)
• Extracting Small Translation Specialists from LLMs by Aggressively Pruning Experts
  di: Martin, Liu O., et al.
  Pubblicazione: (2026)