Privacy-Preserving Heterogeneous Multi-LLM Federated Inference for Cognitive Diagnosis

The paper introduces a federated inference framework that enables multiple commercial large language model (LLM) APIs—such as LLaMA‑3.3‑70B, GPT‑4o‑mini, and Claude‑3‑Haiku—to collaborate on cognitive diagnosis tasks without accessing raw student data or proprietary model internals. Each entity’s predictions are perturbed with Laplace noise to provide epsilon‑local differential privacy, and a residual‑based aggregation scheme mitigates model heterogeneity. Experiments on three educational benchmarks demonstrate strong privacy guarantees with minimal accuracy loss, confirming the framework’s practical usability and cross‑domain generalizability.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

• llms
• benchmarks
• safety