Rethinking the Role of LLMs in Time Series Forecasting

2026-02-16

AI Summary

This study addresses ongoing skepticism regarding the effectiveness of large language models (LLMs) in time series forecasting. Through a large-scale empirical evaluation encompassing 8 billion observations across 17 diverse scenarios, the authors propose LLM4TS—a framework integrating pre-alignment and post-alignment strategies, token-level routing analysis, and prompt engineering. Their findings demonstrate that pre-alignment consistently outperforms post-alignment in over 90% of tasks, revealing complementary roles between LLMs’ pre-trained knowledge and architectural design. Moreover, full-scale LLMs significantly enhance performance in mixed-distribution and cross-domain generalization settings, thereby affirming their critical value in time series prediction.

Technology Category

• Machine Learning: Large Multimodal Models (LMMs)
• Natural Language Processing: (Large) Language Models
• Planning, Routing, and Scheduling: Planning with Language Models

Application Category

• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation
• Search and Retrieval-Augmented AI: Search Tool Learning with LLM: Teaching LLMs to invoke search and make use of retrieved information
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs

Abstract

Large language models (LLMs) have been introduced to time series forecasting (TSF) to incorporate contextual knowledge beyond numerical signals. However, existing studies question whether LLMs provide genuine benefits, often reporting comparable performance without LLMs. We show that such conclusions stem from limited evaluation settings and do not hold at scale. We conduct a large-scale study of LLM-based TSF (LLM4TSF) across 8 billion observations, 17 forecasting scenarios, 4 horizons, multiple alignment strategies, and both in-domain and out-of-domain settings. Our results demonstrate that \emph{LLM4TS indeed improves forecasting performance}, with especially large gains in cross-domain generalization. Pre-alignment outperforming post-alignment in over 90\% of tasks. Both pretrained knowledge and model architecture of LLMs contribute and play complementary roles: pretraining is critical under distribution shifts, while architecture excels at modeling complex temporal dynamics. Moreover, under large-scale mixed distributions, a fully intact LLM becomes indispensable, as confirmed by token-level routing analysis and prompt-based improvements. Overall, Our findings overturn prior negative assessments, establish clear conditions under which LLMs are not only useful, and provide practical guidance for effective model design. We release our code at https://github.com/EIT-NLP/LLM4TSF.

Problem

• large language models
• time series forecasting
• cross-domain generalization
• model evaluation
• distribution shift

Innovation

• LLM4TSF
• time series forecasting
• cross-domain generalization
• pre-alignment
• large-scale evaluation