Federated Language Models Under Bandwidth Budgets: Distillation Rates and Conformal Coverage

arXiv:2605.09986 · stat.ML, cs.CL, cs.LG · Submitted 2026-05-11 · Read on arXiv

stat.ML, cs.CL, cs.LG

Submitted: 2026-05-11

Updated: 2026-10-09

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• RAG — 4× in this paper · explained in 3 episodes
• Consistency — 2× in this paper · explained in 3 episodes
• Distillation — 2× in this paper · explained in 2 episodes
• Quantization — 2× in this paper · explained in 12 episodes
• Accuracy — 1× in this paper · explained in 1 episode
• Aggregation — 1× in this paper · explained in 1 episode
• Calibration — 1× in this paper · explained in 7 episodes
• Federated Probe-Logit Distillation — 1× in this paper

Sources

• FedMD: Heterogenous Federated Learning via Model Distillation
• Efficient Federated Conformal Prediction with Group-Conditional Guarantee
• Federated Conditional Conformal Prediction via Generative Models
• Federated Large Language Models: Current Progress and Future Directions

Related papers

• Behavior of prediction performance metrics with rare events
• Optimal Estimation of Generic Dynamics by Path-Dependent Neural Jump ODEs
• A Posterior-Dynamics Framework for Imaging Inverse Problems with Pretrained Diffusion Priors
• Efficient quadratic entropy with distance sketches
• Embedding-Bias in Conditional Independence Testing
• From Log-Odds to Shapley Values: An Explanatory Geometry for the Weighted Naive Bayes Classifier