ACL Findings2024
LSTPrompt: Large Language Models as Zero-Shot Time Series Forecasters by Long-Short-Term Prompting
Haoxin Liu, Zhiyuan Zhao, Jindong Wang, Harshavardhan Kamarthi, B. Aditya Prakash
Abstract
Time-series forecasting (TSF) finds broad applications in real-world scenarios. Prompting off-the-shelf Large Language Models (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 1 .
Ask Lune
Know this paper in minutes, not an afternoon.
Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.
13 top-tier papers have cited it since. Know what they found before your reviewers do.
Lune can draw on
the full paper · the top-tier papers that cite it · related work
Free to start. No credit card required.
Lineage
- CycleNet: Enhancing Time Series Forecasting through Modeling Periodic Patterns cites Autoformer: Decomposition Transformers with Auto-Correlation for Long-Term Series Forecasting
- CycleNet: Enhancing Time Series Forecasting through Modeling Periodic Patterns cites Informer: Beyond Efficient Transformer for Long Sequence Time-Series Forecasting
- Large Pre-trained time series models for cross-domain Time series analysis tasks cites Informer: Beyond Efficient Transformer for Long Sequence Time-Series Forecasting
- Large Pre-trained time series models for cross-domain Time series analysis tasks cites Language Models are Few-Shot Learners
- Autoformer: Decomposition Transformers with Auto-Correlation for Long-Term Series Forecasting cites Informer: Beyond Efficient Transformer for Long Sequence Time-Series Forecasting
- Autoformer: Decomposition Transformers with Auto-Correlation for Long-Term Series Forecasting cites Language Models are Few-Shot Learners
- Large Language Models are Zero-Shot Reasoners cites Language Models are Few-Shot Learners
- Large Language Models are Zero-Shot Reasoners cites Chain-of-Thought Prompting Elicits Reasoning in Large Language Models
Cited by top-tier papers13
- CycleNet: Enhancing Time Series Forecasting through Modeling Periodic PatternsShengsheng Lin, Weiwei Lin, Xinyi Hu, Wentai Wu et al.NeurIPS 2024 · 213 citations
- Large Pre-trained time series models for cross-domain Time series analysis tasksHarshavardhan Kamarthi, B. Aditya PrakashNeurIPS 2024 · 40 citations
- AgentReview: Exploring Peer Review Dynamics with LLM AgentsYiqiao Jin, Qinlin Zhao, Yiyang Wang, Hao Chen et al.EMNLP 2024 · 24 citations
- Large Language Models Can Be Contextual Privacy Protection LearnersYijia Xiao, Yiqiao Jin, Yushi Bai, Yue Wu et al.EMNLP 2024 · 18 citations
- Can Multimodal LLMs Perform Time Series Anomaly Detection?Xiongxiao Xu, Haoran Wang, Yueqing Liang, Philip S. Yu et al.WWW 2026 · 18 citations
Builds on16
- Language Models are Few-Shot LearnersTom B. Brown, Benjamin Mann, Nick Ryder, Melanie Subbiah et al.NeurIPS 2020 · 64,255 citations
- Chain-of-Thought Prompting Elicits Reasoning in Large Language ModelsJason Wei, Xuezhi Wang, Dale Schuurmans, Maarten Bosma et al.NeurIPS 2022 · 22,562 citations
- Large Language Models are Zero-Shot ReasonersTakeshi Kojima, Shixiang Shane Gu, Machel Reid, Yutaka Matsuo et al.NeurIPS 2022 · 8,168 citations
- Informer: Beyond Efficient Transformer for Long Sequence Time-Series ForecastingHaoyi Zhou, Shanghang Zhang, Jieqi Peng, Shuai Zhang et al.AAAI 2021 · 7,289 citations
- Autoformer: Decomposition Transformers with Auto-Correlation for Long-Term Series ForecastingHaixu Wu, Jiehui Xu, Jianmin Wang, Mingsheng LongNeurIPS 2021 · 5,824 citations
Related papers
- FLAIRR-TS - Forecasting LLM-Agents with Iterative Refinement and Retrieval for Time SeriesGunjan Jalori, Preetika Verma, Sercan Ö. ArikEMNLP Findings 2025 · 1 citation
- From Tokenizer Bias to Backbone Capability: A Controlled Study of LLMs for Time Series ForecastingXinyu Zhang, Shanshan Feng, Xutao Li, Kenghong Lin et al.KDD 2026 · 2 citations
- Time-LLM: Time Series Forecasting by Reprogramming Large Language ModelsMing Jin, Shiyu Wang, Lintao Ma, Zhixuan Chu et al.ICLR 2024 · 915 citations
- In-Context Fine-Tuning for Time-Series Foundation ModelsMatthew Faw, Rajat Sen, Yichen Zhou, Abhimanyu DasICML 2025
- Large Language Models Are Zero-Shot Time Series ForecastersNate Gruver, Marc Finzi, Shikai Qiu, Andrew Gordon WilsonNeurIPS 2023 · 898 citations
