OpenTSLM: Time-Series Language Models for Reasoning over Multivariate Medical Text- and Time-Series Data

• URL: http://arxiv.org/abs/2510.02410v1
• Date: Thu, 02 Oct 2025 09:58:23 GMT
• Title: OpenTSLM: Time-Series Language Models for Reasoning over Multivariate Medical Text- and Time-Series Data
• Authors: Patrick Langer, Thomas Kaar, Max Rosenblattl, Maxwell A. Xu, Winnie Chow, Martin Maritsch, Aradhana Verma, Brian Han, Daniel Seung Kim, Henry Chubb, Scott Ceresnak, Aydin Zahedivash, Alexander Tarlochan Singh Sandhu, Fatima Rodriguez, Daniel McDuff, Elgar Fleisch, Oliver Aalami, Filipe Barata, Paul Schmiedmayer,
• Abstract summary: We present OpenTSLM, a family of Time Series Language Models (TSLMs)<n>OpenTSLM models time series implicitly by concatenating learnable time series tokens with text tokens via soft prompting.<n>We introduce three datasets: HAR-CoT, Sleep-CoT, and ECG-QA-CoT.<n>OpenTSLM models outperform baselines, reaching 69.9 F1 in sleep staging and 65.4 in HAR, compared to 9.05 and 52.2 for finetuned text-only models.
• Score: 35.931918163980605
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: LLMs have emerged as powerful tools for interpreting multimodal data. In medicine, they hold particular promise for synthesizing large volumes of clinical information into actionable insights and digital health applications. Yet, a major limitation remains their inability to handle time series. To overcome this gap, we present OpenTSLM, a family of Time Series Language Models (TSLMs) created by integrating time series as a native modality to pretrained LLMs, enabling reasoning over multiple time series of any length. We investigate two architectures for OpenTSLM. The first, OpenTSLM-SoftPrompt, models time series implicitly by concatenating learnable time series tokens with text tokens via soft prompting. Although parameter-efficient, we hypothesize that explicit time series modeling scales better and outperforms implicit approaches. We thus introduce OpenTSLM-Flamingo, which integrates time series with text via cross-attention. We benchmark both variants against baselines that treat time series as text tokens or plots, across a suite of text-time-series Chain-of-Thought (CoT) reasoning tasks. We introduce three datasets: HAR-CoT, Sleep-CoT, and ECG-QA-CoT. Across all, OpenTSLM models outperform baselines, reaching 69.9 F1 in sleep staging and 65.4 in HAR, compared to 9.05 and 52.2 for finetuned text-only models. Notably, even 1B-parameter OpenTSLM models surpass GPT-4o (15.47 and 2.95). OpenTSLM-Flamingo matches OpenTSLM-SoftPrompt in performance and outperforms on longer sequences, while maintaining stable memory requirements. By contrast, SoftPrompt grows exponentially in memory with sequence length, requiring around 110 GB compared to 40 GB VRAM when training on ECG-QA with LLaMA-3B. Expert reviews by clinicians find strong reasoning capabilities exhibited by OpenTSLMs on ECG-QA. To facilitate further research, we provide all code, datasets, and models open-source.

Related papers

• FiCoTS: Fine-to-Coarse LLM-Enhanced Hierarchical Cross-Modality Interaction for Time Series Forecasting [13.70466880923202]
  Time series forecasting is central to data analysis and web technologies.<n>Large Language Models (LLMs) offers significant potential for this field.<n>We propose FiCoTS, an LLM-enhanced fine-to-coarse framework for multimodal time series forecasting.
  arXiv  Detail & Related papers  (2025-11-29T03:17:26Z)
• SciTS: Scientific Time Series Understanding and Generation with LLMs [53.35994674187729]
  We introduce SciTS, a benchmark spanning 12 scientific domains and 43 tasks.<n>We benchmark 17 models, including text-only LLMs, multimodal LLMs, and unified time series models.<n>We then introduce Time Omni, a framework that equips LLMs with the ability to understand and generate time series.
  arXiv  Detail & Related papers  (2025-09-26T09:25:16Z)
• LLM-PS: Empowering Large Language Models for Time Series Forecasting with Temporal Patterns and Semantics [56.99021951927683]
  Time Series Forecasting (TSF) is critical in many real-world domains like financial planning and health monitoring.<n>Existing Large Language Models (LLMs) usually perform suboptimally because they neglect the inherent characteristics of time series data.<n>We propose LLM-PS to empower the LLM for TSF by learning the fundamental textitPatterns and meaningful textitSemantics from time series data.
  arXiv  Detail & Related papers  (2025-03-12T11:45:11Z)
• A Time Series Multitask Framework Integrating a Large Language Model, Pre-Trained Time Series Model, and Knowledge Graph [1.3654846342364308]
  Time series analysis is crucial in fields like finance, transportation, and industry.<n>This paper proposes a novel time series multitask framework, called LTM, which integrates temporal features with textual descriptions.<n> Experiments on benchmark datasets show that LTM significantly outperforms existing methods.
  arXiv  Detail & Related papers  (2025-03-10T11:25:01Z)
• Language in the Flow of Time: Time-Series-Paired Texts Weaved into a Unified Temporal Narrative [65.84249211767921]
  Texts as Time Series (TaTS) can be plugged into any existing numerical-only time series models.<n>We show that TaTS can enhance predictive performance without modifying model architectures.
  arXiv  Detail & Related papers  (2025-02-13T03:43:27Z)
• ChatTS: Aligning Time Series with LLMs via Synthetic Data for Enhanced Understanding and Reasoning [10.854285913078257]
  This paper introduces ChatTS, a novel MLLM designed for time series analysis.<n>ChatTS treats time series as a modality, similar to how vision MLLMs process images.<n>Time Series Evol-Instruct generates diverse time series Q&As, enhancing the model's reasoning capabilities.
  arXiv  Detail & Related papers  (2024-12-04T08:06:15Z)
• TableTime: Reformulating Time Series Classification as Training-Free Table Understanding with Large Language Models [14.880203496664963]
  Large language models (LLMs) have demonstrated their effectiveness in multivariate time series classification.<n>LLMs directly encode embeddings for time series within the latent space of LLMs from scratch to align with semantic space of LLMs.<n>We propose TableTime, which reformulates MTSC as a table understanding task.
  arXiv  Detail & Related papers  (2024-11-24T07:02:32Z)
• AutoTimes: Autoregressive Time Series Forecasters via Large Language Models [67.83502953961505]
  AutoTimes projects time series into the embedding space of language tokens and autoregressively generates future predictions with arbitrary lengths. We formulate time series as prompts, extending the context for prediction beyond the lookback window. AutoTimes achieves state-of-the-art with 0.1% trainable parameters and over $5times$ training/inference speedup.
  arXiv  Detail & Related papers  (2024-02-04T06:59:21Z)
• Time-LLM: Time Series Forecasting by Reprogramming Large Language Models [110.20279343734548]
  Time series forecasting holds significant importance in many real-world dynamic systems. We present Time-LLM, a reprogramming framework to repurpose large language models for time series forecasting. Time-LLM is a powerful time series learner that outperforms state-of-the-art, specialized forecasting models.
  arXiv  Detail & Related papers  (2023-10-03T01:31:25Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.