Federated Fine-Tuning of LLMs on the Very Edge: The Good, the Bad, the Ugly

Herbert Woisetschlager, Alexander Isenko, Shiqiang Wang, Ruben Mayer, Hans-Arno Jacobsen

Abstract

Examines federated learning approaches for fine-tuning LLMs on edge devices, analyzing privacy guarantees, communication efficiency, and security trade-offs.

Categories

Tags

Framework Mappings

Cite This Resource

@article{llmsec202400032,
  title = {Federated Fine-Tuning of LLMs on the Very Edge: The Good, the Bad, the Ugly},
  author = {Herbert Woisetschlager and Alexander Isenko and Shiqiang Wang and Ruben Mayer and Hans-Arno Jacobsen},
  year = {2024},
  journal = {arXiv preprint},
  url = {https://arxiv.org/abs/2310.17124},
}