Representational capacity in large language models theoretically explains the fundamental limits of what a model can solve, focusing on the ideal potential of a model to provide solutions in principle, independent of whether standard training procedures can actually discover those solutions.

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)

• Large Language Models concept