Gradient Localization Improves Lifelong Pretraining of Language Models

@inproceedings{fernandez2024gradient,
  title = {Gradient Localization Improves Lifelong Pretraining of Language Models},
  author = {Jared Fernandez and Yonatan Bisk and Emma Strubell},
  year = {2024},
  booktitle = {Conference on Empirical Methods in Natural Language Processing},
  eprint = {2411.04448},
  archivePrefix = {arXiv},
  doi = {10.18653/v1/2024.findings-emnlp.949},
  url = {https://arxiv.org/abs/2411.04448},
}