Guilin Deng

Beyond Client Clustering: Fine-Grained Preference Alignment in Federated RLHF via Self-Evolving Routing

Federated Reinforcement Learning from Human Feedback (RLHF) enables the collaborative alignment of Large Language Models (LLMs) while preserving privacy, yet it faces critical bottlenecks arising from data heterogeneity. Existing approaches typically rely on rigid client-level clustering, which over