FERA: Uncertainty-Aware Federated Reasoning for Large Language Models
Researchers have developed FERA, a novel framework for improving large language model reasoning in a federated setting. This approach allows a central server to enhance reasoning by collaborating with multiple clients that hold private demonstration data, without needing to share raw data. FERA uses iterative co-refinement where clients provide reasoning traces with uncertainty estimates, which the server synthesizes to improve future reasoning rounds. The system incorporates Uncertainty-Aware Self-Critique Aggregation (UA-SCA) to revise flawed reasoning steps and improve trust-based weighting, leading to consistent performance gains over existing federated methods. AI
IMPACT Enables collaborative LLM reasoning without centralizing sensitive data, potentially improving model performance across distributed organizations.