Feng et al. (2023a) used circuit complexity theory to prove that finite-depth Transformers can execute tasks by extending their effective depth linearly with the number of generated reasoning steps.

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 (1)

• Transformers concept