LLM4TS: Two-Stage Fine-Tuning for Time-Series Forecasting with Pre-Trained LLMs
LLM4TS: Two-Stage Fine-Tuning for Time-Series Forecasting with Pre-Trained LLMs
Ching Chang,Wen-Chih Peng,Tien-Fu Chen
2023 · DOI: 10.48550/arXiv.2308.08469
arXiv.org · 156 citaten
TLDR
This work leverages pre-trained Large Language Models to enhance time-series forecasting and adopts several Parameter-Efficient Fine-Tuning (PEFT) techniques, which have yielded state-of-the-art results in long-term forecasting.