2025
Filtered not Mixed: Filtering-Based Online Gating for Mixture of Large Language Models
ICLR 2025poster
We propose MoE-F — a formalized mechanism for combining N pre-trained expert Large Language Models (LLMs) in online time-series prediction tasks by adaptively forecasting the best weighting of LLM predictions at every time step. Our mechanism leverages the conditional information in each expert's ru…