Preprint
Aug 2026
LabelFusion-TS: Fusing Large Language Models, Transformer Encoders, and Financial Time Series for Monetary-Policy Stance Classification
It is taken as initial evidence for market time series as an input modality in financial text classification on the task of classifying sentences from Federal Reserve communication as hawkish, dovish, or neutral.
Michael Schlee, Fabian Lukassen, Christoph Weisser
· 0 citations