Deciphering the Factors Influencing the Efficacy of Chain-of-Thought: Probability, Memorization, and Noisy Reasoning

Ähnliche Einträge

• Not-So-Strange Love: Language Models and Generative Linguistic Theories are More Compatible than They Appear
  von: McCoy, R. Thomas
  Veröffentlicht: (2026)
• Identifying and Mitigating the Influence of the Prior Distribution in Large Language Models
  von: Zhang, Liyi, et al.
  Veröffentlicht: (2025)
• Collocational bootstrapping: A hypothesis about the learning of subject-verb agreement in humans and neural networks
  von: Hobbs, Claire, et al.
  Veröffentlicht: (2026)
• When a language model is optimized for reasoning, does it still show embers of autoregression? An analysis of OpenAI o1
  von: McCoy, R. Thomas, et al.
  Veröffentlicht: (2024)
• Diagnosing Memorization in Chain-of-Thought Reasoning, One Token at a Time
  von: Li, Huihan, et al.
  Veröffentlicht: (2025)