Preprint
Filtered not Mixed: Stochastic Filtering-Based Online Gating for Mixture of Large Language Models
Abstract
We propose MoE-F - a formalized mechanism for combining $N$ pre-trained Large
Language Models (LLMs) for online time-series prediction by adaptively
Authors
Saqur R; Kratsios A; Krach F; Limmer Y; Tian J-J; Willes J; Horvath B; Rudzicz F
Publication date
June 5, 2024
DOI
10.48550/arxiv.2406.02969
Preprint server
arXiv