Zhu et al. (2025b) demonstrate that large language models can maintain multiple reasoning trajectories in a state of superposition within continuous latent space, facilitating implicit parallel thinking that exceeds traditional serial reasoning capabilities.

Authors

• Person: Not available Organization: arXiv
  A Survey on the Theory and Mechanism of Large Language Models

Sources

• A Survey on the Theory and Mechanism of Large Language Models arxiv.org arXiv via serper

Referenced by nodes (2)

• Large Language Models concept
• Superposition concept