LLMs Meet Cross-Modal Time Series Analytics: Overview and Directions

2025-07-13

AI Summary

Large language models (LLMs) suffer from cross-modal limitations in time-series analysis due to their text-only pretraining, hindering effective temporal modeling. This paper systematically surveys recent advances in applying LLMs to multimodal time-series analysis. We propose the first classification framework for joint time-series–text modeling, categorizing methodologies into three paradigms: modality translation, representation alignment, and multimodal fusion. We unify and analyze time-series encoding techniques, cross-modal alignment mechanisms, and fusion strategies across downstream tasks—including forecasting, anomaly detection, and interpretability. Key challenges are identified: data sparsity, temporal-semantic misalignment between modalities, and the lack of standardized evaluation protocols. Our work provides both theoretical foundations and a systematic research roadmap for efficiently adapting LLMs to time-series intelligence.

Technology Category

• Machine Learning: Large Multimodal Models (LMMs)
• Natural Language Processing: (Large) Language Models
• Intelligent Robots: Multimodal Perception & Sensor Fusion

Application Category

• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs

Abstract

Large Language Models (LLMs) have emerged as a promising paradigm for time series analytics, leveraging their massive parameters and the shared sequential nature of textual and time series data. However, a cross-modality gap exists between time series and textual data, as LLMs are pre-trained on textual corpora and are not inherently optimized for time series. In this tutorial, we provide an up-to-date overview of LLM-based cross-modal time series analytics. We introduce a taxonomy that classifies existing approaches into three groups based on cross-modal modeling strategies, e.g., conversion, alignment, and fusion, and then discuss their applications across a range of downstream tasks. In addition, we summarize several open challenges. This tutorial aims to expand the practical application of LLMs in solving real-world problems in cross-modal time series analytics while balancing effectiveness and efficiency. Participants will gain a thorough understanding of current advancements, methodologies, and future research directions in cross-modal time series analytics.

Problem

• Bridging cross-modality gap between time series and textual data
• Classifying LLM-based approaches for time series analytics
• Balancing effectiveness and efficiency in real-world applications

Innovation

• LLMs bridge time series and text data
• Taxonomy classifies cross-modal modeling strategies
• Balances effectiveness and efficiency in analytics