A fine-tuned 1.7B language model routes time series forecasting ensembles by reasoning over hybrid text-number series features and retrieved similar cases, beating fixed and learned ensemble baselines on eight benchmarks.
Forecasts in urban transportation planning: Uses, methods, and dilemmas.Climatic Change, 11(1):61–80, 1987
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.LG 1years
2026 1verdicts
CONDITIONAL 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
REATS: LLM Reasoning-based Ensemble Learning for Adaptive Time Series Forecasting
A fine-tuned 1.7B language model routes time series forecasting ensembles by reasoning over hybrid text-number series features and retrieved similar cases, beating fixed and learned ensemble baselines on eight benchmarks.