SafeLM: Unified Privacy-Aware Optimization for Trustworthy Federated Large Language Models

ArXi:2604.16606v1 Announce Type: cross Large language models (LLMs) are increasingly deployed in high-stakes domains, yet a unified treatment of their overlapping safety challenges remains lacking. We present SafeLM, a framework that jointly addresses four pillars of LLM safety: privacy, security, misinformation, and adversarial robustness. SafeLM combines federated