Learning a Generative Meta-Model of LLM Activations

Documenti analoghi

• How do Language Models Bind Entities in Context?
  di: Feng, Jiahai, et al.
  Pubblicazione: (2023)
• Extractive Structures Learned in Pretraining Enable Generalization on Finetuned Facts
  di: Feng, Jiahai, et al.
  Pubblicazione: (2024)
• Monitoring Latent World States in Language Models with Propositional Probes
  di: Feng, Jiahai, et al.
  Pubblicazione: (2024)
• Which Attention Heads Matter for In-Context Learning?
  di: Yin, Kayo, et al.
  Pubblicazione: (2025)
• Shaping capabilities with token-level data filtering
  di: Rathi, Neil, et al.
  Pubblicazione: (2026)