arXiv paper: https://arxiv.org/abs/2404.05405 (last updated April 2024)
Authors: Zeyuan Allen-Zhu and Yuanzhi Li

Slide show (best viewed on a computer)

@inproceedings{AL2024-knowledge3,
  author = {{Allen-Zhu}, Zeyuan and Li, Yuanzhi},
  title = {{Physics of Language Models: Part 3.3, Knowledge Capacity Scaling Laws}},
  booktitle = {Proceedings of the 13th International Conference on Learning Representations},
  series = {ICLR~'25},
  month = apr,
  year = 2025,
  note = {Full version available at \url{http://arxiv.org/abs/2404.05405}}
}