Large Language Model and Digital Twins Empowered Asynchronous Federated Learning for Secure Data Sharing in Intelligent Labeling DOI Creative Commons

Xuanzhu Sheng,

Chao Yu, Xiaolong Cui

и другие.

Mathematics, Год журнала: 2024, Номер 12(22), С. 3550 - 3550

Опубликована: Ноя. 13, 2024

With the advancement of large language model (LLM), demand for data labeling services has increased dramatically. Big models are inseparable from high-quality, specialized scene data, training to deploying application iterations landing generation. However, how achieve intelligent consistency and accuracy improve efficiency in distributed middleware scenarios is main difficulty enhancing quality labeled at present. In this paper, we proposed an asynchronous federated learning optimization method based on combination LLM digital twin technology. By analysising comparing with other existing algorithms, experimental results show that our outperforms algorithms terms performance, such as running time. The validation good performance compared process both solves problems a center.

Язык: Английский

Opportunities, challenges and risks of using artificial intelligence for evidence synthesis DOI
Waldemar Siemens, Erik von Elm, Harald Binder

и другие.

BMJ evidence-based medicine, Год журнала: 2025, Номер unknown, С. bmjebm - 113320

Опубликована: Янв. 9, 2025

Язык: Английский

Процитировано

0
Large Language Model and Digital Twins Empowered Asynchronous Federated Learning for Secure Data Sharing in Intelligent Labeling DOI Creative Commons

Xuanzhu Sheng,

Chao Yu, Xiaolong Cui

и другие.

Mathematics, Год журнала: 2024, Номер 12(22), С. 3550 - 3550

Опубликована: Ноя. 13, 2024

With the advancement of large language model (LLM), demand for data labeling services has increased dramatically. Big models are inseparable from high-quality, specialized scene data, training to deploying application iterations landing generation. However, how achieve intelligent consistency and accuracy improve efficiency in distributed middleware scenarios is main difficulty enhancing quality labeled at present. In this paper, we proposed an asynchronous federated learning optimization method based on combination LLM digital twin technology. By analysising comparing with other existing algorithms, experimental results show that our outperforms algorithms terms performance, such as running time. The validation good performance compared process both solves problems a center.

Язык: Английский

Процитировано

0