Pith. sign in

REVIEW 19 cited by

Large Language Models for Time Series: A Survey

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2402.01801 v3 pith:OI5MZABP submitted 2024-02-02 cs.LG cs.AIcs.CL

Xiyuan Zhang , Ranak Roy Chowdhury , Rajesh K. Gupta , Jingbo Shang This is my paper
classification cs.LGcs.AIcs.CL
keywords llmsseriestimesurveyanalysisdatalanguagetext
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Large Language Models (LLMs) have seen significant use in domains such as natural language processing and computer vision. Going beyond text, image and graphics, LLMs present a significant potential for analysis of time series data, benefiting domains such as climate, IoT, healthcare, traffic, audio and finance. This survey paper provides an in-depth exploration and a detailed taxonomy of the various methodologies employed to harness the power of LLMs for time series analysis. We address the inherent challenge of bridging the gap between LLMs' original text data training and the numerical nature of time series data, and explore strategies for transferring and distilling knowledge from LLMs to numerical time series analysis. We detail various methodologies, including (1) direct prompting of LLMs, (2) time series quantization, (3) aligning techniques, (4) utilization of the vision modality as a bridging mechanism, and (5) the combination of LLMs with tools. Additionally, this survey offers a comprehensive overview of the existing multimodal time series and text datasets and delves into the challenges and future opportunities of this emerging field. We maintain an up-to-date Github repository which includes all the papers and datasets discussed in the survey.

Discussion (0). Sign in to comment.

Forward citations

Cited by 19 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. Efficient and Adaptive Human Activity Recognition via LLM Backbones

    cs.LG 2026-05 unverdicted novelty 7.0 of 10

    Pretrained LLMs adapted via convolutional projections and LoRA act as efficient frozen backbones for sensor-based human activity recognition, delivering strong data efficiency and cross-dataset transfer.

  2. TS-Agent: Understanding and Reasoning Over Raw Time Series via Iterative Insight Gathering

    cs.AI 2025-10 unverdicted novelty 7.0 of 10

    TS-Agent is an agentic framework that uses LLMs only for evidence-based reasoning while delegating extraction to raw time series tools, matching or exceeding baselines on four benchmarks with largest gains on reasoning tasks.

  3. Data Mixing Agent: Learning to Re-weight Domains for Continual Pre-training

    cs.LG 2025-07 unverdicted novelty 7.0 of 10

    An RL agent learns domain re-weighting policies from evaluation feedback to improve balanced performance in continual pre-training of LLMs across source and target domains.

  4. A Cost-Effective Multimodal LLM Reasoning Framework for Question Answering over Irregular Clinical Time Series

    cs.AI 2026-07 conditional novelty 6.0 of 10

    ClinPRISM reaches 49.83% average accuracy on CLIR-Bench irregular clinical time-series QA using a 4B LLM, 16 temporal tokens, and 0.15 s/question.

  5. CLIR-Bench: Benchmarking Multimodal Question Answering over Irregular Clinical Time Series

    cs.CL 2026-07 conditional novelty 6.0 of 10

    CLIR-Bench shows generalist and time-series LLMs struggle to ground clinical answers in sparse irregular ICU evidence, with top accuracy near 50% and weak causal evidence use.

  6. CausalMoE: A Billion-Scale Multimodal Foundation Model for Granger Causal Discovery with Pattern-Routed Heterogeneous Experts

    cs.LG 2026-06 unverdicted novelty 6.0 of 10

    CausalMoE is a multimodal foundation model with pattern-routed heterogeneous experts and LLM/VLM integration that claims new SOTA performance on supervised and few-shot Granger causal discovery benchmarks.

  7. InA-Probe: Instruction-Aware Active Probing for Time Series Forecasting with LLMs

    cs.AI 2026-06 unverdicted novelty 6.0 of 10

    InA-Probe improves LLM time series forecasting via instruction-aware active probing, outperforming baselines with up to 37% error reduction on seven benchmarks in one-for-all and zero-shot settings.

  8. Spectra as Language: Large Language Models for Scalable Stellar Parameter and Abundance Inference

    astro-ph.IM 2026-05 unverdicted novelty 6.0 of 10

    Two-stage LLM framework infers stellar parameters and ~20 elemental abundances from spectra, showing performance gains with increasing data volume.

  9. Time Series Augmented Generation for Financial Applications

    cs.AI 2026-04 unverdicted novelty 6.0 of 10

    TSAG lets LLMs use external tools for financial time series analysis, with a new benchmark showing capable agents achieve near-perfect tool accuracy and minimal hallucination.

  10. Natural Language Interfaces for Spatial and Temporal Databases: A Comprehensive Overview of Methods, Taxonomy, and Future Directions

    cs.DB 2026-03 unverdicted novelty 6.0 of 10

    A literature survey that taxonomizes methods, datasets, and evaluation practices for natural language interfaces to geospatial and temporal databases while identifying recurring trends and future directions.

  11. TSAQA: Time Series Analysis Question And Answering Benchmark

    cs.AI 2026-01 conditional novelty 6.0 of 10

    TSAQA provides 210k QA samples across 13 domains and six tasks, showing current LLMs score at most 65.08% zero-shot and struggle most with temporal-order reasoning.

  12. BEDTime: A Unified Benchmark for Automatically Describing Time Series

    cs.CL 2025-09 conditional novelty 6.0 of 10

    BEDTime benchmark tests 17 models on describing time series structure and finds vision-language models outperform dedicated time-series-language models and language-only approaches, with all models fragile to robustne...

  13. Time Series Forecasting as Reasoning: A Slow-Thinking Approach with Reinforced LLMs

    cs.LG 2025-06 unverdicted novelty 6.0 of 10

    Time-R1 trains LLMs via supervised fine-tuning followed by reinforcement learning with a time-series-specific reward and non-uniform GRIP sampling to enable multi-step reasoning that improves forecasting accuracy.

  14. Spectra as Language: Large Language Models for Scalable Stellar Parameter and Abundance Inference

    astro-ph.IM 2026-05 unverdicted novelty 5.0 of 10

    A two-stage LLM framework infers stellar parameters and ~20 elemental abundances from spectra, with performance improving systematically as training data volume increases.

  15. Spectra as Language: Large Language Models for Scalable Stellar Parameter and Abundance Inference

    astro-ph.IM 2026-05 unverdicted novelty 5.0 of 10

    A two-stage LLM framework infers stellar parameters and ~20 elemental abundances from spectra, with performance improving as training data increases.

  16. Large Language Models for Sequential Decision-Making: Improving In-Context Learning via Supervised Fine-Tuning

    cs.LG 2026-05 unverdicted novelty 5.0 of 10

    Supervised fine-tuning of pretrained LLMs on offline trajectories yields better few-shot sequential decision-making than in-context-only baselines, with a theoretical suboptimality bound derived for linear MDPs by int...

  17. Physics-Aware LLM-Based Probabilistic Wind Power Scenario Generation under Extreme Icing Conditions

    eess.SY 2026-04 unverdicted novelty 5.0 of 10

    A physics-aware LLM framework generates high-fidelity probabilistic wind power scenarios under extreme icing by enforcing physical constraints like power limits and ramp rates on trajectories from real SCADA data.

  18. ELATE: Evolutionary Language model for Automated Time-series Engineering

    cs.LG 2025-08 conditional novelty 5.0 of 10

    An LLM-guided evolutionary feature engineering method for time-series forecasting reduces RMSE by 8.4% on average across seven datasets.

  19. Technology-assisted Personalized Yoga for Better Health -- Challenges and Outlook

    cs.HC 2025-08 unverdicted novelty 4.0 of 10

    A vision statement for personalized yoga decision support whose claimed content cannot be verified, because the supplied full text is a different paper on maritime drift prediction.

Pith tools