Predicting the Unpredictable: LLM-powered Long-term Chaotic Time Series Forecasting under Short-term Observations
PAC-LLM is proposed, a phase-space-aware adaptive fusion framework for long-term chaotic time series forecasting powered by LLMs that leverages learned phase-space features and textual information to fully enable LLM's time series forecasting capacity.
Yue Yao, Bo-Han Jiang
· 0 citations