Federated LLM aggregation stops trusting pairwise similarity: LoRA updates become hypergraph nodes, and malicious weights drop to near zero
A federated LLM server now treats each agent's LoRA update as a node in a hypergraph and passes messages along hyperedges to spot and suppress poisoned knowledge, beating Multi-Krum, FoolsGold and FLTrust on AG News and Yahoo! Answers.