works on
dynamic client participation 1hierarchical federated learning 1incentive allocation 1large language models 1model unlearning 1parameter-efficient fine-tuning 1

From the 1 of 7 linked papers with an AI index.

activity
20242026
collaborators
Showing cs.CEShow all

1 paper · 1 filter

cs.CE2026

HermesHFL: Incentive-Compatible Hierarchical Federated Unlearning for Dynamic LLM Fine-Tuning

Chenxi Sun, Minghui Liwang, Wusi He +8

The paper introduces HermesHFL, a hierarchical federated learning system that enables selective unlearning and dynamic client participation for fine‑tuning large language models us…