@article{whylargermodelslearnmoreeffectsofcapacit,
  title = {Why Larger Models Learn More: Effects of Capacity, Interference, and Rare-Task Retention},
  author = {Jing Huang and Daniel Wurgaft and Rachit Bansal and Laura Ruis and Naomi Saphra and David Alvarez-Melis and Andrew Kyle Lampinen and Christopher Potts and Ekdeep Singh Lubana},
  year = {2026},
  eprint = {2605.29548},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2605.29548},
}