CAARL: In-Context Learning for Interpretable Co-Evolving Time Series Forecasting

2026-04-20

AI Summary

This work addresses the challenge of forecasting co-evolving time series characterized by complex dependencies and non-stationary dynamics. To this end, the authors propose the CAARL framework, which decomposes time series into autoregressive segments, constructs a temporal dependency graph, and serializes this graph into natural language narratives. These narratives are then processed by a large language model (LLM) to perform in-context learning, enabling chain-of-thought–style interpretable reasoning for prediction. Evaluated on multiple real-world datasets, CAARL achieves predictive performance on par with or superior to state-of-the-art methods while offering a transparent and traceable decision-making process, effectively balancing accuracy with model interpretability.

Technology Category

• Machine Learning: Time-Series/Data Streams
• Reasoning under Uncertainty: Causality
• Natural Language Processing: Interpretability, Analysis, and Evaluation of NLP Models

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• Web Mining and Content Analysis: Large pretrained models with web data

Abstract

In this paper we investigate forecasting coevolving time series that feature intricate dependencies and nonstationary dynamics by using an LLM Large Language Models approach We propose a novel modeling approach named ContextAware ARLLM CAARL that provides an interpretable framework to decode the contextual dynamics influencing changes in coevolving series CAARL decomposes time series into autoregressive segments constructs a temporal dependency graph and serializes this graph into a narrative to allow processing by LLM This design yields a chainofthoughtlike reasoning path where intermediate steps capture contextual dynamics and guide forecasts in a transparent manner By linking prediction to explicit reasoning traces CAARL enhances interpretability while maintaining accuracy Experiments on realworld datasets validate its effectiveness positioning CAARL as a competitive and interpretable alternative to stateoftheart forecasting methods

Problem

• co-evolving time series
• interpretable forecasting
• nonstationary dynamics
• intricate dependencies
• time series forecasting

Innovation

• in-context learning
• interpretable forecasting
• co-evolving time series
• large language models
• temporal dependency graph