FedBPT: Efficient Federated Black-box Prompt Tuning for Large Language Models

Researchers from Duke University and NVIDIA introduced FedBPT, a method for efficient federated black-box prompt tuning of large language models, presented at ICML 2024. The approach enables collaborative fine-tuning without sharing raw data or model parameters, addressing privacy and communication constraints.

Research Labs All Research Labs Spatial Intelligence Applied Research Autonomous Vehicles Deep Imagination Publications AI Playground New and Featured AI Art Gallery NGC Demos Research Areas AI & Machine Learning 3D Deep Learning Computer Vision Robotics All Areas Careers Academic Collaborations Government Collaborations Graduate Fellowship Internships Research Openings Research Scientists Meet the Team Licensing Skip to main content Artificial Intelligence Computing Leadership from NVIDIA Login Research Labs All Research Labs Spatial Intelligence Applied Research Autonomous Vehicles Deep Imagination Publications AI Playground New and Featured AI Art Gallery NGC Demos Research Areas AI & Machine Learning 3D Deep Learning Computer Vision Robotics All Areas Careers Academic Collaborations Government Collaborations Graduate Fellowship Internships Research Openings Research Scientists Meet the Team Licensing Search Search Enter the terms you wish to search for. Publications FedBPT: Efficient Federated Black-box Prompt Tuning for Large Language Models FedBPT: Efficient Federated Black-box Prompt Tuning for Large Language Models Authors Jingwei Sun Duke University Ziyue Xu Hongxu Danny Yin Dong Yang Daguang Xu Yudong Liu Duke University Zhixu Du Duke University Yiran Chen Duke University Holger Roth Publication Date Sunday, July 21, 2024 Published in International Conference on Machine Learning 2024 Research Area Artificial Intelligence and Machine Learning Generative AI Natural Language Processing