On the Representational Capacity of Neural Language Models with Chain-of-Thought Reasoning

Documenti analoghi

• Transformers Can Represent $n$-gram Language Models
  di: Svete, Anej, et al.
  Pubblicazione: (2024)
• Unique Hard Attention: A Tale of Two Sides
  di: Jerad, Selim, et al.
  Pubblicazione: (2025)
• An Algebraic View of the Expressivity of Recurrent Language Models
  di: Nowak, Franz, et al.
  Pubblicazione: (2026)
• Context-Free Recognition with Transformers
  di: Jerad, Selim, et al.
  Pubblicazione: (2026)
• Revisiting Padded Transformer Expressivity: Which Architectural Choices Matter and Which Don't
  di: Svete, Anej, et al.
  Pubblicazione: (2026)