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

arXiv: https://arxiv.org/abs/2402.16132 · HTML: https://mlsanity.com/paper/2402.16132/

## Key facts

- Cited by 59 papers in the map (data through 14 Oct 2026).
- Builds on 20 of its 31 references that are in the map.
- First posted on arXiv 25 Feb 2024.

## Builds on (most cited first, 20 of 20)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [Large Language Models are Zero-Shot Reasoners](https://mlsanity.com/paper/2205.11916/) (2022)
- [Informer: Beyond Efficient Transformer for Long Sequence Time-Series Forecasting](https://mlsanity.com/paper/2012.07436/) (2020)
- [A Time Series is Worth 64 Words: Long-term Forecasting with Transformers](https://mlsanity.com/paper/2211.14730/) (2022)
- [Autoformer: Decomposition Transformers with Auto-Correlation for Long-Term Series Forecasting](https://mlsanity.com/paper/2106.13008/) (2021)
- [FEDformer: Frequency Enhanced Decomposed Transformer for Long-term Series Forecasting](https://mlsanity.com/paper/2201.12740/) (2022)
- [Large Language Models Are Human-Level Prompt Engineers](https://mlsanity.com/paper/2211.01910/) (2022)
- [Modeling Long- and Short-Term Temporal Patterns with Deep Neural Networks](https://mlsanity.com/paper/1703.07015/) (2017)
- [N-BEATS: Neural basis expansion analysis for interpretable time series forecasting](https://mlsanity.com/paper/1905.10437/) (2019)
- [One Fits All:Power General Time Series Analysis by Pretrained LM](https://mlsanity.com/paper/2302.11939/) (2023)
- [Large Language Models Are Zero-Shot Time Series Forecasters](https://mlsanity.com/paper/2310.07820/) (2023)
- [Time Series Forecasting With Deep Learning: A Survey](https://mlsanity.com/paper/2004.13408/) (2020)
- [Monash Time Series Forecasting Archive](https://mlsanity.com/paper/2105.06643/) (2021)
- [Pretrained Transformers as Universal Computation Engines](https://mlsanity.com/paper/2103.05247/) (2021)
- [Text-to-Audio Generation using Instruction-Tuned LLM and Latent Diffusion Model](https://mlsanity.com/paper/2304.13731/) (2023)
- [Darts: User-Friendly Modern Machine Learning for Time Series](https://mlsanity.com/paper/2110.03224/) (2021)
- [Large Pre-trained time series models for cross-domain Time series analysis tasks](https://mlsanity.com/paper/2311.11413/) (2023)

## Built on by (most cited first, 30 of 59)

- [CycleNet: Enhancing Time Series Forecasting through Modeling Periodic Patterns](https://mlsanity.com/paper/2409.18479/) (2024)
- [AgentReview: Exploring Peer Review Dynamics with LLM Agents](https://mlsanity.com/paper/2406.12708/) (2024)
- [Time-MQA: Time Series Multi-Task Question Answering with Context Enhancement](https://mlsanity.com/paper/2503.01875/) (2025)
- [Time-MMD: Multi-Domain Multimodal Dataset for Time Series Analysis](https://mlsanity.com/paper/2406.08627/) (2024)
- [Time Series Forecasting via Reasoning: A Slow-Thinking Approach with Reinforcement Fine-Tuned LLMs](https://mlsanity.com/paper/2506.10630/) (2025)
- [Empowering Time Series Analysis with Foundation Models: A Comprehensive Survey](https://mlsanity.com/paper/2405.02358/) (2024)
- [Can LLMs Serve As Time Series Anomaly Detectors?](https://mlsanity.com/paper/2408.03475/) (2024)
- [TimeRAG: BOOSTING LLM Time Series Forecasting via Retrieval-Augmented Generation](https://mlsanity.com/paper/2412.16643/) (2024)
- [See it, Think it, Sorted: Large Multimodal Models are Few-shot Time Series Anomaly Analyzers](https://mlsanity.com/paper/2411.02465/) (2024)
- [How Can Time Series Analysis Benefit From Multiple Modalities? A Survey and Outlook](https://mlsanity.com/paper/2503.11835/) (2025)
- [BRIDGE: Bootstrapping Text to Control Time-Series Generation via Multi-Agent Iterative Optimization and Diffusion Modeling](https://mlsanity.com/paper/2503.02445/) (2025)
- [A Survey of AIOps in the Era of Large Language Models](https://mlsanity.com/paper/2507.12472/) (2025)
- [From Values to Tokens: An LLM-Driven Framework for Context-aware Time Series Forecasting via Symbolic Discretization](https://mlsanity.com/paper/2508.09191/) (2025)
- [Can Multimodal LLMs Perform Time Series Anomaly Detection?](https://mlsanity.com/paper/2502.17812/) (2025)
- [TS-Reasoner: Aligning Time Series Foundation Models with LLM Reasoning](https://mlsanity.com/paper/2510.03519/) (2025)
- [AlphaCast: A Human Wisdom-LLM Intelligence Co-Reasoning Framework for Interactive Time Series Forecasting](https://mlsanity.com/paper/2511.08947/) (2025)
- [MicroRemed: Benchmarking LLMs in Microservices Remediation](https://mlsanity.com/paper/2511.01166/) (2025)
- [MemCast: Memory-Driven Time Series Forecasting with Experience-Conditioned Reasoning](https://mlsanity.com/paper/2602.03164/) (2026)
- [TableTime: Reformulating Time Series Classification as Training-Free Table Understanding with Large Language Models](https://mlsanity.com/paper/2411.15737/) (2024)
- [MoTime: A Dataset Suite for Multimodal Time Series Forecasting](https://mlsanity.com/paper/2505.15072/) (2025)
- [TimeRecipe: A Time-Series Forecasting Recipe via Benchmarking Module Level Effectiveness](https://mlsanity.com/paper/2506.06482/) (2025)
- [Teaching Time Series to See and Speak: Forecasting with Aligned Visual and Textual Perspectives](https://mlsanity.com/paper/2506.24124/) (2025)
- [Rethinking Multimodal Time-Series Forecasting Evaluation](https://mlsanity.com/paper/2607.06973/) (2026)
- [FLAIRR-TS -- Forecasting LLM-Agents with Iterative Refinement and Retrieval for Time Series](https://mlsanity.com/paper/2508.19279/) (2025)
- [BALM-TSF: Balanced Multimodal Alignment for LLM-Based Time Series Forecasting](https://mlsanity.com/paper/2509.00622/) (2025)
- [UniCL: A Universal Contrastive Learning Framework for Large Time Series Models](https://mlsanity.com/paper/2405.10597/) (2024)
- [FLUID-LLM: Learning Computational Fluid Dynamics with Spatiotemporal-aware Large Language Models](https://mlsanity.com/paper/2406.04501/) (2024)
- [DELPHYNE: A Pre-Trained Model for General and Financial Time Series](https://mlsanity.com/paper/2506.06288/) (2025)
- [Is More Context Always Better? Examining LLM Reasoning Capability for Time Interval Prediction](https://mlsanity.com/paper/2601.10132/) (2026)
- [E2E-REME: Towards End-to-End Microservices Auto-Remediation via Experience-Simulation Reinforcement Fine-Tuning](https://mlsanity.com/paper/2604.11094/) (2026)

## Abstract (arXiv)

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.