SciTS: Scientific Time Series Understanding and Generation with LLMs

• URL: http://arxiv.org/abs/2510.03255v1
• Date: Fri, 26 Sep 2025 09:25:16 GMT
• Title: SciTS: Scientific Time Series Understanding and Generation with LLMs
• Authors: Wen Wu, Ziyang Zhang, Liwei Liu, Xuenan Xu, Junlin Liu, Ke Fan, Qitan Lv, Jimin Zhuang, Chen Zhang, Zheqi Yuan, Siyuan Hou, Tianyi Lin, Kai Chen, Bowen Zhou, Chao Zhang,
• Abstract summary: 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.
• Score: 53.35994674187729
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: The scientific reasoning ability of large language models (LLMs) has recently attracted significant attention. Time series, as a fundamental modality in scientific data, presents unique challenges that are often overlooked in current multimodal LLMs, which either encode numerical sequences as text or convert them into images. Such approaches may be insufficient for comprehensive scientific time series understanding and generation. Existing unified time series models typically specialise in either forecasting or analysis, and their effectiveness on non-periodic, heterogeneous scientific signals remains unclear. To address these gaps, we introduce SciTS, a benchmark spanning 12 scientific domains and 43 tasks, with over 50k+ instances, both univariate and multivariate signals ranging from $10^0$ to $10^7$ in length and up to 10~MHz in frequency. We benchmark 17 models, including text-only LLMs, multimodal LLMs, and unified time series models, and find that general-purpose LLMs exhibit stronger generalisability than specialised time series models, while representing time series as text or images limits their performance due to excessively long sequences and loss of numerical precision, respectively. We then introduce TimeOmni, a framework that equips LLMs with the ability to understand and generate time series while remaining compatible with general-purpose LLM training. This work fills a gap in both dedicated benchmarks and modelling frameworks for scientific time series, paving the way for LLMs to understand and generate complex temporal scientific data.

Related papers

• Multi-scale hypergraph meets LLMs: Aligning large language models for time series analysis [14.045113722315579]
  We propose MSH-LLM, a Multi-Scale Hypergraph method that aligns Large Language Models for time series analysis.<n> Specifically, a hyperedging mechanism is designed to enhance the multi-scale semantic information of time series semantic space.<n>A mixture of prompts (MoP) mechanism is introduced to provide contextual information and enhance the ability of LLMs to understand the multi-scale temporal patterns of time series.
  arXiv  Detail & Related papers  (2026-02-04T09:47:00Z)
• TS-Reasoner: Aligning Time Series Foundation Models with LLM Reasoning [17.69077698133793]
  Time series reasoning is crucial to decision-making in diverse domains, including finance, energy usage, traffic, weather, and scientific discovery.<n>LLMs often struggle with the numerical understanding of time series data.<n>We develop a training recipe that applies instruction finetuning after the alignment pretraining.
  arXiv  Detail & Related papers  (2025-10-03T21:20:54Z)
• Causal Graph Fuzzy LLMs: A First Introduction and Applications in Time Series Forecasting [0.0]
  This study presents a new frame of LLMs named CGF-LLM using GPT-2 combined with fuzzy time series (FTS) and causal graph.<n>The key objective is to convert numerical time series into interpretable forms through the parallel application of fuzzification and causal analysis.
  arXiv  Detail & Related papers  (2025-07-22T21:03:13Z)
• Time-RA: Towards Time Series Reasoning for Anomaly with LLM Feedback [55.284574165467525]
  Time-series Reasoning for Anomaly (Time-RA) transforms classical time series anomaly detection into a generative, reasoning-intensive task.<n>Also, we introduce the first real-world multimodal benchmark dataset, RATs40K, explicitly annotated for anomaly reasoning.
  arXiv  Detail & Related papers  (2025-07-20T18:02:50Z)
• 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)
• Can Multimodal LLMs Perform Time Series Anomaly Detection? [55.534264764673296]
  We propose VisualTimeAnomaly benchmark to evaluate MLLMs in time series anomaly detection (TSAD)<n>Our approach transforms time series numerical data into the image format and feed these images into various MLLMs.<n>In total, VisualTimeAnomaly contains 12.4k time series images spanning 3 scenarios and 3 anomaly granularities with 9 anomaly types across 8 MLLMs.
  arXiv  Detail & Related papers  (2025-02-25T03:37:43Z)
• 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)
• Time Series Forecasting with LLMs: Understanding and Enhancing Model Capabilities [46.02234423159257]
  Large language models (LLMs) have been applied in many fields and have developed rapidly in recent years.<n>Recent works treat large language models as emphzero-shot time series reasoners without further fine-tuning.<n>Our study shows that LLMs perform well in predicting time series with clear patterns and trends, but face challenges with datasets lacking periodicity.
  arXiv  Detail & Related papers  (2024-02-16T17:15:28Z)
• 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.