mlsanityData to 14 Oct 2026

Insight Miner: A Time Series Analysis Dataset for Cross-Domain Alignment with Natural Language

arXiv 2512.11251 ↗First posted 12 Dec 2025cs.LGcited by 3

Not on the map. Why?

Abstract (arXiv)

Time-series data is critical across many scientific and industrial domains, including environmental analysis, agriculture, transportation, and finance. However, mining insights from this data typically requires deep domain expertise, a process that is both time-consuming and labor-intensive. In this paper, we propose Insight Miner, a large-scale multimodal model (LMM) designed to generate high-quality, comprehensive time-series descriptions enriched with domain-specific knowledge. To facilitate this, we introduce TS-InsightsfootnoteAvailable at hrefhttps://huggingface.co/datasets/zhykoties/time-series-language-alignmenthttps://huggingface.co/datasets/zhykoties/time-series-language-alignment., the first general-domain dataset for time series and language alignment. TS-Insights contains 100k time-series windows sampled from 20 forecasting datasets. We construct this dataset using a novel agentic workflow, where we use statistical tools to extract features from raw time series before synthesizing them into coherent trend descriptions with GPT-4. Following instruction tuning on TS-Insights, Insight Miner outperforms state-of-the-art multimodal models, such as LLaVA citepliu2023llava and GPT-4, in generating time-series descriptions and insights. Our findings suggest a promising direction for leveraging LMMs in time series analysis, and serve as a foundational step toward enabling LLMs to interpret time series as a native input modality.

Key facts. Cited by 3 papers in the map (data through 14 Oct 2026). Builds on 7 of its 16 references that are in the map. First posted on arXiv 12 Dec 2025.

Builds on

7 of 16 references.

References · 7

  1. 2023LLaVA-Med: Training a Large Language-and-Vision Assistant for Biomedicine in One Daycited by 1,305
  2. 2017Modeling Long- and Short-Term Temporal Patterns with Deep Neural Networkscited by 879
  3. 2023One Fits All:Power General Time Series Analysis by Pretrained LMcited by 632
  4. 2021Monash Time Series Forecasting Archivecited by 267
  5. 2022PromptCast: A New Prompt-based Learning Paradigm for Time Series Forecastingcited by 172
  6. 2023Temporal Data Meets LLM -- Explainable Financial Time Series Forecastingcited by 77
  7. 2023FinVis-GPT: A Multimodal Large Language Model for Financial Chart Analysiscited by 28

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 3.

3 papers.

  1. 2026Thoth: Mid-Training Bridges LLMs to Time Series Understandingcited by 4
  2. 2026Rationale-Grounded In-Context Learning for Time Series Reasoning with Multimodal Large Language Modelscited by 0
  3. 2026WaveTLM: Reliable Time-Series Language Modeling through Task Compilationcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025Enhancing LLMs for Time Series Forecasting via Structure-Guided Cross-Modal Alignment
  2. 2025Enhancing Time Series Forecasting via Multi-Level Text Alignment with LLMs
  3. 2025BALM-TSF: Balanced Multimodal Alignment for LLM-Based Time Series Forecasting
  4. 2026Multi-scale hypergraph meets LLMs: Aligning large language models for time series analysis
  5. 2024Understanding Why Large Language Models Can Be Ineffective in Time Series Analysis: The Impact of Modality Alignment
  6. 2025ChronoSteer: Bridging Large Language Model and Time Series Foundation Model via Synthetic Cross-Modal Alignment Dataset
  7. 2025Context-Alignment: Activating and Enhancing LLM Capabilities in Time Series
  8. 2025Multimodal Language Models with Modality-Specific Experts for Financial Forecasting from Interleaved Sequences of Text and Time Series