Kim et al. (2025a) aim to mechanistically diagnose benchmark composition by decomposing performance into contributions from discrete cognitive abilities, addressing the issue where single-scalar scores obscure the complex combination of skills required for a task.

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)

• cognitive ability concept