Towards Cross-Modality Modeling for Time Series Analytics: A Survey in the LLM Era
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866916719933521920 |
|---|---|
| author | Liu, Chenxi Zhou, Shaowen Xu, Qianxiong Miao, Hao Long, Cheng Li, Ziyue Zhao, Rui |
| author_facet | Liu, Chenxi Zhou, Shaowen Xu, Qianxiong Miao, Hao Long, Cheng Li, Ziyue Zhao, Rui |
| contents | The proliferation of edge devices has generated an unprecedented volume of time series data across different domains, motivating various well-customized methods. Recently, Large Language Models (LLMs) have emerged as a new paradigm for time series analytics by leveraging the shared sequential nature of textual data and time series. However, a fundamental cross-modality gap between time series and LLMs exists, as LLMs are pre-trained on textual corpora and are not inherently optimized for time series. Many recent proposals are designed to address this issue. In this survey, we provide an up-to-date overview of LLMs-based cross-modality modeling for time series analytics. We first introduce a taxonomy that classifies existing approaches into four groups based on the type of textual data employed for time series modeling. We then summarize key cross-modality strategies, e.g., alignment and fusion, and discuss their applications across a range of downstream tasks. Furthermore, we conduct experiments on multimodal datasets from different application domains to investigate effective combinations of textual data and cross-modality strategies for enhancing time series analytics. Finally, we suggest several promising directions for future research. This survey is designed for a range of professionals, researchers, and practitioners interested in LLM-based time series modeling. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2505_02583 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Towards Cross-Modality Modeling for Time Series Analytics: A Survey in the LLM Era Liu, Chenxi Zhou, Shaowen Xu, Qianxiong Miao, Hao Long, Cheng Li, Ziyue Zhao, Rui Machine Learning The proliferation of edge devices has generated an unprecedented volume of time series data across different domains, motivating various well-customized methods. Recently, Large Language Models (LLMs) have emerged as a new paradigm for time series analytics by leveraging the shared sequential nature of textual data and time series. However, a fundamental cross-modality gap between time series and LLMs exists, as LLMs are pre-trained on textual corpora and are not inherently optimized for time series. Many recent proposals are designed to address this issue. In this survey, we provide an up-to-date overview of LLMs-based cross-modality modeling for time series analytics. We first introduce a taxonomy that classifies existing approaches into four groups based on the type of textual data employed for time series modeling. We then summarize key cross-modality strategies, e.g., alignment and fusion, and discuss their applications across a range of downstream tasks. Furthermore, we conduct experiments on multimodal datasets from different application domains to investigate effective combinations of textual data and cross-modality strategies for enhancing time series analytics. Finally, we suggest several promising directions for future research. This survey is designed for a range of professionals, researchers, and practitioners interested in LLM-based time series modeling. |
| title | Towards Cross-Modality Modeling for Time Series Analytics: A Survey in the LLM Era |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2505.02583 |