CIRF: Tokenizing Chain-of-Thoughts into Reusable Functional Units for Efficient Latent Reasoning in Large Language Models

Documenti analoghi

• SPOT: Span-level Pause-of-Thought for Efficient and Interpretable Latent Reasoning in Large Language Models
  di: Chu, Yunlong, et al.
  Pubblicazione: (2026)
• NUMCoT: Numerals and Units of Measurement in Chain-of-Thought Reasoning using Large Language Models
  di: Xu, Ancheng, et al.
  Pubblicazione: (2024)
• Beyond Chains of Thought: Benchmarking Latent-Space Reasoning Abilities in Large Language Models
  di: Hagendorff, Thilo, et al.
  Pubblicazione: (2025)
• Evaluating Chain-of-Thought Reasoning through Reusability and Verifiability
  di: Aggarwal, Shashank, et al.
  Pubblicazione: (2026)
• Reasoning Beyond Language: A Comprehensive Survey on Latent Chain-of-Thought Reasoning
  di: Chen, Xinghao, et al.
  Pubblicazione: (2025)