Research map / Time series / Long-term forecasting
LagLLM: LLM-empowered lead–lag dependency learning for spatial-temporal time series forecasting
Binqing Wu, Jian Zhou, Zongjiang Shang, Ling Chen
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (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 |
|---|---|---|---|
| add the lead-lag graph (ablation) | LagLLM · PEMS08 | MAE: 14.14 -> 13.21 | Improved |
| add the lead-lag graph (ablation) | LagLLM · ChinaAQI | MAE: 19.74 -> 19.14 | Improved |
| add the data-driven mask to the hybrid graph (ablation) | LagLLM · PEMS08 | MAE: 13.58 -> 13.21 | Improved |
| add the knowledge-driven (LLM semantic) mask (ablation) | LagLLM · PEMS08 | MAE: 13.63 -> 13.21 | Improved |
| add structural token sorting (ablation) | LagLLM · PEMS08 | MAE: 13.34 -> 13.21 | Improved |
| sort tokens by lead-lag structure instead of spatial topology (ablation) | LagLLM · PEMS08 | MAE: 13.28 -> 13.21 | Improved |
| add the grouping loss (ablation) | LagLLM · PEMS08 | MAE: 13.24 -> 13.21 | Improved |
| add lead-lag criteria to the prompt (ablation) | LagLLM · PEMS08 | MAE: 13.33 -> 13.21 | Improved |
| use hybrid template-plus-learnable prompt instead of fully learnable prompt (ablation) | LagLLM · PEMS08 | MAE: 13.59 -> 13.21 | Improved |
| replace GPT-2 backbone with LLaMA-3-8B (ablation) | LagLLM · PEMS08 | MAE: 13.21 -> 13.19 | Improved |
| LagLLM vs STD-PLM with 5% training data | STD-PLM · PEMS07 (5% training data) | MAE: 32.48 -> 30.07 | Improved |
| LagLLM vs STD-PLM with 10% training data | STD-PLM · PEMS07 (10% training data) | MAE: 26.37 -> 23.82 | Improved |
Closest papers by meaning
- FSTLLM: Spatio-Temporal LLM for Few Shot Time Series Forecasting (ICML 2025 · similarity 0.89)
- Time-LLM: Time Series Forecasting by Reprogramming Large Language Models (ICLR 2024 · similarity 0.88)
- STEM-LTS: Integrating Semantic-Temporal Dynamics in LLM-driven Time Series Analysis (AAAI 2025 · similarity 0.87)
- On the Integration of Spatial-Temporal Knowledge: A Lightweight Approach to Atmospheric Time Series Forecasting (NeurIPS 2025 · similarity 0.86)
- $S^2$IP-LLM: Semantic Space Informed Prompt Learning with LLM for Time Series Forecasting (ICML 2024 · similarity 0.86)
- TimeXL: Explainable Multi-modal Time Series Prediction with LLM-in-the-Loop (NeurIPS 2025 · similarity 0.86)
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.
