@inproceedings{kowsher-etal-2025-llm,
    title = "{LLM}-Mixer: Multiscale Mixing in {LLM}s for Time Series Forecasting",
    author = "Kowsher, Md  and
      Sobuj, Md. Shohanur Islam  and
      Prottasha, Nusrat Jahan  and
      Alanis, E. Alejandro  and
      Garibay, Ozlem  and
      Yousefi, Niloofar",
    editor = "Chang, Shuaichen  and
      Hulsebos, Madelon  and
      Liu, Qian  and
      Chen, Wenhu  and
      Sun, Huan",
    booktitle = "Proceedings of the 4th Table Representation Learning Workshop",
    month = jul,
    year = "2025",
    address = "Vienna, Austria",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/acl25-workshop-ingestion/2025.trl-1.12/",
    pages = "156--165",
    ISBN = "979-8-89176-268-8",
    abstract = "Time series forecasting is a challenging task, especially when dealing with data that contains both short-term variations and long-term trends. In this study, we introduce LLM-Mixer, a novel framework that combines multiscale time-series decomposition with the power of pre-trained Large Language Models (LLMs). LLM-Mixer breaks down time-series data into multiple temporal resolutions using downsampling and processes these multiscale representations with a frozen LLM, guided by a carefully designed text prompt that encodes information about the dataset{'}s features and structure. To understand the role of downsampling, we conduct a detailed analysis using Neural Tangent Kernel (NTK) distance, showing that incorporating multiple scales improves the model{'}s learning dynamics.We evaluate LLM-Mixer across a diverse set of forecasting tasks, including long-term multivariate, short-term multivariate, and long-term univariate scenarios. Experimental results demonstrate that LLM-Mixer achieves competitive performance compared to recent state-of-the-art models across various forecasting horizons."
}