Large Language Model Federated Learning with Blockchain and Unlearning for Cross-Organizational Collaboration
Xuhan Zuo, Minghao Wang, Tianqing Zhu, Shui Yu, Wanlei Zhou
TL;DR
Cross-organizational LLM training faces privacy, trust, and regulatory constraints; the authors propose a hybrid public/private blockchain federated learning framework augmented with LoRA-based unlearning and multi-agent $Q$-learning to enable secure, transparent collaboration. The framework supports transparent model update sharing on a public ledger while keeping sensitive computations on private chains, with data forgetting achieved via LoRA adaptation in $E_u$ epochs. Each organization acts as an agent using $Q$-learning to optimize participation and resource allocation, aligning individual incentives with collective model quality. Experimental results on IMDB and Twitter show comparable final accuracy to retraining from scratch while enabling targeted forgetting and with manageable blockchain overhead, demonstrating practical privacy-preserving collaboration; case studies in education and healthcare illustrate real-world applicability for privacy, auditability, and regulatory compliance.
Abstract
Large language models (LLMs) have transformed the way computers understand and process human language, but using them effectively across different organizations remains still difficult. When organizations work together to improve LLMs, they face several main challenges. First, organizations hesitate to share their valuable data with others. Second, competition between organizations creates trust problems during collaboration. Third, new privacy laws require organizations to be able to delete specific data when requested, which is especially difficult when multiple organizations are learning from shared data. Traditional federated learning approaches do not address these interconnected challenges, particularly in scenarios where participants cannot fully trust each other or the central aggregator. To overcome these limitations, we propose a hybrid blockchain-based federated learning framework that uniquely combines public and private blockchain architectures with multi-agent reinforcement learning. Our framework enables transparent sharing of model update through the public blockchain while protecting sensitive computations in private chains. Each organization operates as an intelligent agent, using Q-learning to optimize its participation strategy and resource allocation, thus aligning individual incentives with collective goals. Notably, we introduce an efficient unlearning mechanism based on Low-Rank Adaptation (LoRA) that enables selective removal of specific data contributions without compromising the model's overall performance. Through extensive experimentation on real-world datasets, we demonstrate that our framework effectively balances privacy protection, trust establishment, and regulatory compliance while maintaining high model performance.