How new data permeates LLM knowledge and how to dilute it

Documenti analoghi

• Learning and Unlearning of Fabricated Knowledge in Language Models
  di: Sun, Chen, et al.
  Pubblicazione: (2024)
• Contextually Guided Transformers via Low-Rank Adaptation
  di: Zhmoginov, Andrey, et al.
  Pubblicazione: (2025)
• Continual HyperTransformer: A Meta-Learner for Continual Few-Shot Learning
  di: Vladymyrov, Max, et al.
  Pubblicazione: (2023)
• Long Context In-Context Compression by Getting to the Gist of Gisting
  di: Petrov, Aleksandar, et al.
  Pubblicazione: (2025)
• Narrowing the Focus: Learned Optimizers for Pretrained Models
  di: Kristiansen, Gus, et al.
  Pubblicazione: (2024)