Research map / Time series / Foundation models for time series
Large Language Models Are Zero-Shot Time Series Forecasters
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| LLMTime zero-shot forecasting vs trained baselines (ARIMA, TCN, N-HiTS) | GPT-3 / LLaMA-2 70B · Darts | NLL and CRPS | Helped |
| LLMTime vs PromptCast prompting | GPT-3 / LLaMA-2 70B · Darts | CRPS and MAE | Helped |
| add spaces between digits in tokenization (ablation) | GPT-3 · Australian Wine (Darts) | forecast error | Helped |
| add spaces between digits in tokenization (ablation) | LLaMA-2 · Australian Wine (Darts) | forecast error | Hurt |
| use chat/aligned model instead of base model | LLaMA-2 · Darts | NLL/D and CRPS | Hurt |
| use GPT-4 instead of GPT-3 | LLMTime · Darts | CRPS | Hurt |
| use stronger base model (higher MMLU) | LLMTime · Darts | NLL/D and CRPS | Helped |
| reduce fraction of training data available | LLMTime vs baselines · Darts | NLL | Mixed |
| encode missing values as NaN text instead of interpolation | LLaMA-2 70B · Darts corrupted | NLL | Helped |
| extend prediction horizon from 96 to 192 | LLMTime (LLaMA-2 70B) · Informer datasets | MAE | Hurt |
Closest papers by meaning
- Time-LLM: Time Series Forecasting by Reprogramming Large Language Models (ICLR 2024 · similarity 0.91)
- AutoTimes: Autoregressive Time Series Forecasters via Large Language Models (NeurIPS 2024 · similarity 0.91)
- A decoder-only foundation model for time-series forecasting (ICML 2024 · similarity 0.91)
- GPT4MTS: Prompt-based Large Language Model for Multimodal Time-series Forecasting (AAAI 2024 · similarity 0.90)
- Are Language Models Actually Useful for Time Series Forecasting? (NeurIPS 2024 · similarity 0.90)
- ChatTime: A Unified Multimodal Time Series Foundation Model Bridging Numerical and Textual Data (AAAI 2025 · similarity 0.90)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.