LSTPrompt: Large Language Models as Zero-Shot Time Series Forecasters by Long-Short-Term Prompting

Publication

Implementation of the paper "LSTPrompt: Large Language Models as Zero-Shot Time Series Forecasters by Long-Short-Term Prompting."

Venue: ACL Findings 2024

Authors: Haoxin Liu*, Leo Zhiyuan Zhao*, Jindong Wang, Harshavardhan Kamarthi, B.Aditya Prakash

Paper + Appendix: https://arxiv.org/abs/2402.16132

Run LSTPrompt

Try LSTPrompt through the quick demo demo.ipynb notebook.

Contact

If you have any questions about the code, please contact:

Haoxin Liu at hliu763[at]gatech[dot]edu;

Leo Zhiyuan Zhao at leozhao1997[at]gatech[dot]edu.

Citation

If you find our work useful, please cite our work:

@article{liu2024lstprompt,
  title={LSTPrompt: Large Language Models as Zero-Shot Time Series Forecasters by Long-Short-Term Prompting},
  author={Liu, Haoxin and Zhao, Zhiyuan and Wang, Jindong and Kamarthi, Harshavardhan and Prakash, B Aditya},
  journal={arXiv preprint arXiv:2402.16132},
  year={2024}
}

Acknowledgement

This repo is constructed based on the following repos:

[https://github.com/ngruver/llmtime]