Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
162 tokens/sec
GPT-4o
7 tokens/sec
Gemini 2.5 Pro Pro
45 tokens/sec
o3 Pro
4 tokens/sec
GPT-4.1 Pro
38 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

LSTPrompt: Large Language Models as Zero-Shot Time Series Forecasters by Long-Short-Term Prompting (2402.16132v1)

Published 25 Feb 2024 in cs.CL and cs.AI

Abstract: Time-series forecasting (TSF) finds broad applications in real-world scenarios. Prompting off-the-shelf LLMs demonstrates strong zero-shot TSF capabilities while preserving computational efficiency. However, existing prompting methods oversimplify TSF as language next-token predictions, overlooking its dynamic nature and lack of integration with state-of-the-art prompt strategies such as Chain-of-Thought. Thus, we propose LSTPrompt, a novel approach for prompting LLMs in zero-shot TSF tasks. LSTPrompt decomposes TSF into short-term and long-term forecasting sub-tasks, tailoring prompts to each. LSTPrompt guides LLMs to regularly reassess forecasting mechanisms to enhance adaptability. Extensive evaluations demonstrate consistently better performance of LSTPrompt than existing prompting methods, and competitive results compared to foundation TSF models.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (36)
  1. Gpt-4 technical report. arXiv preprint arXiv:2303.08774.
  2. Epideep: Exploiting embeddings for epidemic forecasting. In Proceedings of the 25th ACM SIGKDD international conference on knowledge discovery & data mining, pages 577–586.
  3. Language models are few-shot learners. Advances in neural information processing systems, 33:1877–1901.
  4. Llm4ts: Two-stage fine-tuning for time-series forecasting with pre-trained llms. arXiv preprint arXiv:2308.08469.
  5. A decoder-only foundation model for time-series forecasting. arXiv preprint arXiv:2310.10688.
  6. A review on time series forecasting techniques for building energy consumption. Renewable and Sustainable Energy Reviews, 74:902–924.
  7. Azul Garza and Max Mergenthaler-Canseco. 2023. Timegpt-1. arXiv preprint arXiv:2310.03589.
  8. Text-to-audio generation using instruction-tuned llm and latent diffusion model. arXiv preprint arXiv:2304.13731.
  9. Monash time series forecasting archive. arXiv preprint arXiv:2105.06643.
  10. Large Language Models Are Zero Shot Time Series Forecasters. In Advances in Neural Information Processing Systems.
  11. Tabllm: Few-shot classification of tabular data with large language models. In International Conference on Artificial Intelligence and Statistics, pages 5549–5581. PMLR.
  12. Darts: User-friendly modern machine learning for time series. The Journal of Machine Learning Research, 23(1):5442–5447.
  13. Time-llm: Time series forecasting by reprogramming large language models. arXiv preprint arXiv:2310.01728.
  14. Camul: Calibrated and accurate multi-view time-series forecasting. In Proceedings of the ACM Web Conference 2022, pages 3174–3185.
  15. Harshavardhan Kamarthi and B Aditya Prakash. 2023. Large pre-trained time series models for cross-domain time series analysis tasks. arXiv preprint arXiv:2311.11413.
  16. Large language models are zero-shot reasoners. Advances in neural information processing systems, 35:22199–22213.
  17. Modeling long-and short-term temporal patterns with deep neural networks. In The 41st international ACM SIGIR conference on research & development in information retrieval, pages 95–104.
  18. Bryan Lim and Stefan Zohren. 2021. Time-series forecasting with deep learning: a survey. Philosophical Transactions of the Royal Society A, 379(2194):20200209.
  19. Pretrained transformers as universal computation engines. arXiv preprint arXiv:2103.05247, 1.
  20. Elizbar A Nadaraya. 1964. On estimating regression. Theory of Probability & Its Applications, 9(1):141–142.
  21. A time series is worth 64 words: Long-term forecasting with transformers. arXiv preprint arXiv:2211.14730.
  22. N-beats: Neural basis expansion analysis for interpretable time series forecasting. arXiv preprint arXiv:1905.10437.
  23. Francis EH Tay and Lijuan Cao. 2001. Application of support vector machines in financial time series forecasting. omega, 29(4):309–317.
  24. Llama 2: Open foundation and fine-tuned chat models. arXiv preprint arXiv:2307.09288.
  25. Attention is all you need. Advances in neural information processing systems, 30.
  26. Chain-of-thought prompting elicits reasoning in large language models. Advances in Neural Information Processing Systems, 35:24824–24837.
  27. Christopher Williams and Carl Rasmussen. 1995. Gaussian processes for regression. Advances in neural information processing systems, 8.
  28. Autoformer: Decomposition transformers with auto-correlation for long-term series forecasting. Advances in Neural Information Processing Systems, 34:22419–22430.
  29. Hao Xue and Flora D Salim. 2023. Promptcast: A new prompt-based learning paradigm for time series forecasting. IEEE Transactions on Knowledge and Data Engineering.
  30. Large language models as optimizers. arXiv preprint arXiv:2309.03409.
  31. Toward a foundation model for time series data. In Proceedings of the 32nd ACM International Conference on Information and Knowledge Management, pages 4400–4404.
  32. G Peter Zhang. 2003. Time series forecasting using a hybrid arima and neural network model. Neurocomputing, 50:159–175.
  33. Informer: Beyond efficient transformer for long sequence time-series forecasting. In Proceedings of the AAAI conference on artificial intelligence, volume 35, pages 11106–11115.
  34. Fedformer: Frequency enhanced decomposed transformer for long-term series forecasting. In International Conference on Machine Learning, pages 27268–27286. PMLR.
  35. One fits all: Power general time series analysis by pretrained lm. arXiv preprint arXiv:2302.11939.
  36. Large language models are human-level prompt engineers. arXiv preprint arXiv:2211.01910.
Citations (14)
View on Semantic Scholar

Summary

We haven't generated a summary for this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize Now
X Twitter Logo Streamline Icon: https://streamlinehq.com

Tweets