CTRL: Control-Based Time Series Forecasting with LLM-Guided Residual Learning
cs.LG, cs.CL
Submitted: 2026-09-20
Updated: 2026-10-08
Comments: Published in Findings of the Association for Computational Linguistics: ACL 2026. 18 pages, 9 figures, 22 tables
Journal ref: Findings of the Association for Computational Linguistics: ACL 2026, pages 21952-21968
Code: https://github.com/mfriendly/CTRL
License: http://creativecommons.org/licenses/by/4.0/
The gist: Time series forecasting underpins critical decision-making across diverse domains.
Terminology
Abstract
Time series forecasting underpins critical decision-making across diverse domains. While large language models (LLMs) offer promising reasoning capabilities, existing LLM-based time series forecasting approaches either reduce them to numerical predictors that bypass their strengths, or allow direct forecast generation that destabilizes predictions in non-stationary settings. We introduce CTRL, a framework that decouples semantic reasoning from quantitative prediction. A frozen backbone generates base forecasts, while specialized LLM agents function as controllers that analyze backbone prediction errors through decomposed trend, seasonal, and irregular components, grounding reasoning in interpretable temporal structure. Each agent outputs compact control signals that a lightweight residual decoder translates into forecast corrections. CTRL incorporates label-free test-time adaptation that detects distribution shift from input statistics alone and readapts control signals with only 3-24 LLM calls via caching. CTRL is explicitly designed to improve robustness under non-stationary temporal dynamics and distribution shift, while remaining competitive on highly stationary time series where adaptive correction provides limited additional benefit.
Sources
- LLM4TS: Aligning Pre-Trained LLMs as Data-Efficient Time-Series Forecasters
- TimeXL: Explainable Multi-modal Time Series Prediction with LLM-in-the-Loop
- TimeCMA: Towards LLM-Empowered Multivariate Time Series Forecasting via Cross-Modality Alignment
- Spatial-Temporal Large Language Model for Traffic Prediction
- Tokenization counts: the impact of tokenization on arithmetic in frontier LLMs
- When Does Multimodality Lead to Better Time Series Forecasting?
- Unveiling the Potential of Text in High-Dimensional Time Series Forecasting
Related papers
- Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
- AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
- Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
- Convergence issues in Relational Concept Analysis based on AOC-posets
- Beliefs Beyond Posteriors: Local-Consistency Optimisation for Bayesian Neural Networks
- Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks