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

arXiv: https://arxiv.org/abs/2510.02410 · HTML: https://mlsanity.com/paper/2510.02410/

## Key facts

- Cited by 36 papers in the map (data through 14 Oct 2026).
- Placed in Time series reasoning, one of 17 directions in LLM reasoning.
- Builds on 16 of its 56 references that are in the map.
- First posted on arXiv 2 Oct 2025.

## Placed in

- LLM reasoning / [Time series reasoning](https://mlsanity.com/lr/time-series-reasoning/)

## Builds on (most cited first, 16 of 16)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [Flamingo: a Visual Language Model for Few-Shot Learning](https://mlsanity.com/paper/2204.14198/) (2022)
- [Gemma: Open Models Based on Gemini Research and Technology](https://mlsanity.com/paper/2403.08295/) (2024)
- [OpenFlamingo: An Open-Source Framework for Training Large Autoregressive Vision-Language Models](https://mlsanity.com/paper/2308.01390/) (2023)
- [GIFT-Eval: A Benchmark For General Time Series Forecasting Model Evaluation](https://mlsanity.com/paper/2410.10393/) (2024)
- [Large Language Models are Few-Shot Health Learners](https://mlsanity.com/paper/2305.15525/) (2023)
- [ChatTime: A Unified Multimodal Time Series Foundation Model Bridging Numerical and Textual Data](https://mlsanity.com/paper/2412.11376/) (2024)
- [MEDEC: A Benchmark for Medical Error Detection and Correction in Clinical Notes](https://mlsanity.com/paper/2412.19260/) (2024)
- [SensorLM: Learning the Language of Wearable Sensors](https://mlsanity.com/paper/2506.09108/) (2025)
- [SensorLLM: Aligning Large Language Models with Motion Sensors for Human Activity Recognition](https://mlsanity.com/paper/2410.10624/) (2024)
- [Towards Time Series Reasoning with LLMs](https://mlsanity.com/paper/2409.11376/) (2024)
- [MedualTime: A Dual-Adapter Language Model for Medical Time Series-Text Multimodal Learning](https://mlsanity.com/paper/2406.06620/) (2024)
- [Time2Lang: Bridging Time-Series Foundation Models and Large Language Models for Health Sensing Beyond Prompting](https://mlsanity.com/paper/2502.07608/) (2025)
- [Byte Pair Encoding for Efficient Time Series Forecasting](https://mlsanity.com/paper/2505.14411/) (2025)

## Built on by (most cited first, 30 of 36)

- [TSRBench: A Comprehensive Multi-task Multi-modal Time Series Reasoning Benchmark for Generalist Models](https://mlsanity.com/paper/2601.18744/) (2026)
- [SleepLM: Natural-Language Intelligence for Human Sleep](https://mlsanity.com/paper/2602.23605/) (2026)
- [HEARTS: Benchmarking LLM Reasoning on Health Time Series](https://mlsanity.com/paper/2603.06638/) (2026)
- [STReasoner: Empowering LLMs for Spatio-Temporal Reasoning in Time Series via Spatial-Aware Reinforcement Learning](https://mlsanity.com/paper/2601.03248/) (2026)
- [ARFBench: Benchmarking Time Series Question Answering Ability for Software Incident Response](https://mlsanity.com/paper/2604.21199/) (2026)
- [Adaptive Time Series Reasoning via Segment Selection](https://mlsanity.com/paper/2602.18645/) (2026)
- [ECG-Reasoning-Benchmark: A Benchmark for Evaluating Clinical Reasoning Capabilities in ECG Interpretation](https://mlsanity.com/paper/2603.14326/) (2026)
- [How Well Do Multimodal Models Reason on ECG Signals?](https://mlsanity.com/paper/2603.00312/) (2026)
- [Wearable Foundation Models Should Go Beyond Static Encoders](https://mlsanity.com/paper/2603.19564/) (2026)
- [LLaTiSA: Towards Difficulty-Stratified Time Series Reasoning from Visual Perception to Semantics](https://mlsanity.com/paper/2604.17295/) (2026)
- [TS-Haystack: A Multi-Task Retrieval Benchmark for Long-Context Time-Series Reasoning](https://mlsanity.com/paper/2602.14200/) (2026)
- [MILM: Large Language Models for Multimodal Irregular Time Series with Informative Sampling](https://mlsanity.com/paper/2605.13711/) (2026)
- [Representing Time Series as Structured Programs for LLM Reasoning](https://mlsanity.com/paper/2606.12481/) (2026)
- [WEQA: Wearable hEalth Question Answering with Query-Adaptive Agentic Reasoning](https://mlsanity.com/paper/2606.18147/) (2026)
- [OpenMHC: Accelerating the Science of Wearable Foundation Models](https://mlsanity.com/paper/2607.16235/) (2026)
- [Toward Reasoning-Centric Time-Series Analysis](https://mlsanity.com/paper/2510.13029/) (2025)
- [TSQAgent: Rating Time Series Data Quality via Dedicated Agentic Reasoning](https://mlsanity.com/paper/2606.03629/) (2026)
- [TRACE-TS: Attribution-Grounded and Traceable Sensor-Language Reasoning for Human Activity Understanding](https://mlsanity.com/paper/2608.00200/) (2026)
- [Sonar-TS: Search-Then-Verify Natural Language Querying for Time Series Databases](https://mlsanity.com/paper/2602.17001/) (2026)
- [TRIAGE: Dialectical Reasoning for Explainable Risk Prediction on Irregularly Sampled Medical Time Series with LLMs](https://mlsanity.com/paper/2606.09030/) (2026)
- [The Capacity of Thought: Benchmarking Llama 3.2 in Semantic fMRI Neural Language Decoding and Improving the Huth Encoding-Model Baseline](https://mlsanity.com/paper/2607.12079/) (2026)
- [When Derived Measurements Mislead: Quantifying and Mitigating LLM Over-Trust with Privileged-Modality Reliability Evidence](https://mlsanity.com/paper/2607.28421/) (2026)
- [TimeRLM: Recursive Language Models Enable Precise Anomaly Localization in Long-Context Time-Series](https://mlsanity.com/paper/2608.03391/) (2026)
- [Financial Numerical Prediction and Allocation as Token Generation](https://mlsanity.com/paper/2608.09880/) (2026)
- [When Text and Numbers Disagree: Evidence Arbitration in Large Language Models](https://mlsanity.com/paper/2608.20116/) (2026)
- [Large language models in medical time series analysis](https://mlsanity.com/paper/2609.22262/) (2026)
- [TimeInteract: Towards Real-Time Interactive Intelligence for Streaming Time Series](https://mlsanity.com/paper/2609.26389/) (2026)
- [TimeBraid: Unifying Time Series and Language for Understanding and Forecasting](https://mlsanity.com/paper/2609.29792/) (2026)
- [PPG-LM: A Photoplethysmography-Language Model with Multi-Level Clinical Alignment](https://mlsanity.com/paper/2609.33516/) (2026)
- [TRACE: Expert-Aligned ECG Representation Learning with Rigorous Benchmarking and Real-World Validation in Acute Cardiac Care](https://mlsanity.com/paper/2609.34088/) (2026)

## Abstract (arXiv)

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.