Huang et al. (2024e) observe a strong linear relationship between compression efficiency and downstream task performance, using knowledge, commonsense, coding, and mathematical reasoning as proxies for intelligence.

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 (3)

• intelligence concept
• knowledge concept
• coding concept