Emergence of a High-Dimensional Abstraction Phase in Language Transformers

Documenti analoghi

• Tracing Computation Density in LLMs
  di: Kervadec, Corentin, et al.
  Pubblicazione: (2026)
• Sparse or Dense? A Mechanistic Estimation of Computation Density in Transformer-based LLMs
  di: Kervadec, Corentin, et al.
  Pubblicazione: (2026)
• Prediction hubs are context-informed frequent tokens in LLMs
  di: Nielsen, Beatrix M. G., et al.
  Pubblicazione: (2025)
• Not a nuisance but a useful heuristic: Outlier dimensions favor frequent tokens in language models
  di: Macocco, Iuri, et al.
  Pubblicazione: (2025)
• Evil twins are not that evil: Qualitative insights into machine-generated prompts
  di: Rakotonirina, Nathanaël Carraz, et al.
  Pubblicazione: (2024)