mlsanityData to 7 Oct 2026

Time-MQA: Time Series Multi-Task Question Answering with Context Enhancement

arXiv 2503.01875 ↗First posted 26 Feb 2025cs.CL cs.AI cs.LGcited by 74

Not on the map. Why?

Cited by 27 in LLM reasoning, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

Time series data are foundational in finance, healthcare, and energy domains. However, most existing methods and datasets remain focused on a narrow spectrum of tasks, such as forecasting or anomaly detection. To bridge this gap, we introduce Time Series Multi-Task Question Answering (Time-MQA), a unified framework that enables natural language queries across multiple time series tasks - numerical analytical tasks and open-ended question answering with reasoning. Central to Time-MQA is the TSQA dataset, a large-scale dataset containing ~200k question-answer pairs derived from diverse time series spanning environment, traffic, etc. This comprehensive resource covers various time series lengths and promotes robust model development. We further demonstrate how continually pre-training large language models (Mistral 7B, Llama-3 8B, and Qwen-2.5 7B) on the TSQA dataset enhanced time series reasoning capabilities, moving beyond mere numeric tasks and enabling more advanced and intuitive interactions with temporal data. The complete TSQA dataset, models, user study questionnaires for evaluation, and other related materials have been open-sourced.

Key facts. Cited by 74 papers in the map (data through 7 Oct 2026). Builds on 40 of its 75 references that are in the map. First posted on arXiv 26 Feb 2025.

Builds on

40 of 75 references.

References · 40

  1. 2023GPT-4 Technical Reportcited by 18,132
  2. 2024The Llama 3 Herd of Modelscited by 14,192
  3. 2023LLaMA: Open and Efficient Foundation Language Modelscited by 13,958
  4. 2018HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answeringcited by 3,686
  5. 2020Informer: Beyond Efficient Transformer for Long Sequence Time-Series Forecastingcited by 2,141
  6. 2020Constructing A Multi-hop QA Dataset for Comprehensive Evaluation of Reasoning Stepscited by 1,259
  7. 2024Chronos: Learning the Language of Time Seriescited by 712
  8. 2020Time Series Forecasting With Deep Learning: A Surveycited by 457
  9. 2023ToolQA: A Dataset for LLM Question Answering with External Toolscited by 273
  10. 2025Agentic Retrieval-Augmented Generation: A Survey on Agentic RAGcited by 242
  11. 2024TimeXer: Empowering Transformers for Time Series Forecasting with Exogenous Variablescited by 241
  12. 2020Time Series Data Augmentation for Deep Learning: A Surveycited by 225
28 more
  1. 2024Timer: Generative Pre-trained Transformers Are Large Time Series Modelscited by 198
  2. 2023LLM Lies: Hallucinations are not Bugs, but Features as Adversarial Examplescited by 177
  3. 2022Deep Learning for Time Series Anomaly Detection: A Surveycited by 130
  4. 2023Large Models for Time Series and Spatio-Temporal Data: A Survey and Outlookcited by 109
  5. 2024ChatTS: Aligning Time Series with LLMs via Synthetic Data for Enhanced Understanding and Reasoningcited by 95
  6. 2024ChatTime: A Unified Multimodal Time Series Foundation Model Bridging Numerical and Textual Datacited by 92
  7. 2024A Survey of Large Language Models for Financial Applications: Progress, Prospects and Challengescited by 86
  8. 2024MMToM-QA: Multimodal Theory of Mind Question Answeringcited by 84
  9. 2024Language Models Still Struggle to Zero-shot Reason about Time Seriescited by 81
  10. 2024Context is Key: A Benchmark for Forecasting with Essential Textual Informationcited by 78
  11. 2023Deep Learning for Time Series Classification and Extrinsic Regression: A Current Surveycited by 68
  12. 2024Instruction Pre-Training: Language Models are Supervised Multitask Learnerscited by 63
  13. 2024LSTPrompt: Large Language Models as Zero-Shot Time Series Forecasters by Long-Short-Term Promptingcited by 56
  14. 2024FinTextQA: A Dataset for Long-form Financial Question Answeringcited by 54
  15. 2024Evaluating Large Language Models on Time Series Feature Understanding: A Comprehensive Taxonomy and Benchmarkcited by 38
  16. 2024TSI-Bench: Benchmarking Time Series Imputationcited by 33
  17. 2024A Picture is Worth A Thousand Numbers: Enabling LLMs Reason about Time Series via Visualizationcited by 31
  18. 2024Trajectory Data Management and Mining: A Survey from Deep Learning to the LLM Eracited by 23
  19. 2022Tele-Knowledge Pre-training for Fault Analysiscited by 18
  20. 2024Intervention-Aware Forecasting: Breaking Historical Limits from a System Perspectivecited by 16
  21. 2024To Generate or to Retrieve? On the Effectiveness of Artificial Contexts for Medical Open-Domain Question Answeringcited by 15
  22. 2025Achieving Time Series Reasoning Requires Rethinking Model Design, Tasks Formulation, and Evaluationcited by 15
  23. 2024MedualTime: A Dual-Adapter Language Model for Medical Time Series-Text Multimodal Learningcited by 11
  24. 2024SyllabusQA: A Course Logistics Question Answering Datasetcited by 9
  25. 2023SGDP: A Stream-Graph Neural Network Based Data Prefetchercited by 7
  26. 2024FusionSF: Fuse Heterogeneous Modalities in a Vector Quantized Framework for Robust Solar Power Forecastingcited by 6
  27. 2024FinQAPT: Empowering Financial Decisions with End-to-End LLM-driven Question Answering Pipelinecited by 6
  28. 2024Maximizing the Impact of Deep Learning on Subseasonal-to-Seasonal Climate Forecasting: The Essential Role of Optimizationcited by 3

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 28; 2026: 46.

74 papers.

Sort:

By area:

  1. 2025MTBench: A Multimodal Time Series Benchmark for Temporal Reasoning and Question Answeringcited by 50
  2. 2025TimeXL: Explainable Multi-modal Time Series Prediction with LLM-in-the-Loopcited by 39
  3. 2025Aurora: Towards Universal Generative Multimodal Time Series Forecastingcited by 28
  4. 2026TimeART: Towards Agentic Time Series Reasoning via Tool-Augmentationcited by 25
  5. 2025Multi-modal Time Series Analysis: A Tutorial and Surveycited by 24
  6. 2025TimeOmni-1: Incentivizing Complex Reasoning with Time Series in Large Language Modelscited by 24
  7. 2025A Survey of Reasoning and Agentic Systems in Time Series with Large Language Modelscited by 21
  8. 2025How Can Time Series Analysis Benefit From Multiple Modalities? A Survey and Outlookcited by 20
  9. 2025TimeMaster: Training Time-Series Multimodal LLMs to Reason via Reinforcement Learningcited by 16
  10. 2026TSRBench: A Comprehensive Multi-task Multi-modal Time Series Reasoning Benchmark for Generalist Modelscited by 14
  11. 2025SciTS: Scientific Time Series Understanding and Generation with LLMscited by 13
  12. 2025BEDTime: A Unified Benchmark for Automatically Describing Time Seriescited by 11
38 more
  1. 2026TSAQA: Time Series Analysis Question And Answering Benchmarkcited by 8
  2. 2026HEARTS: Benchmarking LLM Reasoning on Health Time Seriescited by 8
  3. 2025DanmakuTPPBench: A Multi-modal Benchmark for Temporal Point Process Modeling and Understandingcited by 7
  4. 2025Time-RA: Towards Time Series Reasoning for Anomaly Diagnosis with LLM Feedbackcited by 7
  5. 2025TS-Agent: Understanding and Reasoning Over Raw Time Series via Iterative Insight Gatheringcited by 7
  6. 2026STReasoner: Empowering LLMs for Spatio-Temporal Reasoning in Time Series via Spatial-Aware Reinforcement Learningcited by 7
  7. 2025TelecomTS: A Multi-Modal Observability Dataset for Time Series and Language Analysiscited by 5
  8. 2025Reasoning on Time-Series for Financial Technical Analysiscited by 5
  9. 2026TimeSeriesExamAgent: Creating Time Series Reasoning Benchmarks at Scalecited by 5
  10. 2026ARFBench: Benchmarking Time Series Question Answering Ability for Software Incident Responsecited by 5
  11. 2025Cross-Domain Conditional Diffusion Models for Time Series Imputationcited by 4
  12. 2025AXIS: Explainable Time Series Anomaly Detection with Large Language Modelscited by 4
  13. 2025Eliciting Chain-of-Thought Reasoning for Time Series Analysis using Reinforcement Learningcited by 4
  14. 2026TimeOmni-VL: Unified Models for Time Series Understanding and Generationcited by 4
  15. 2026CLIR-Bench: Benchmarking Multimodal Question Answering over Irregular Clinical Time Seriescited by 4
  16. 2025A Modular Multitask Reasoning Framework Integrating Spatio-temporal Models and LLMscited by 3
  17. 2025Augur: Modeling Covariate Causal Associations in Time Series via Large Language Modelscited by 3
  18. 2025TimeSense:Making Large Language Models Proficient in Time-Series Analysiscited by 3
  19. 2026Time Series Reasoning via Process-Verifiable Thinking Data Synthesis and Scheduling for Tailored LLM Reasoningcited by 3
  20. 2026Adaptive Time Series Reasoning via Segment Selectioncited by 3
  21. 2026Thoth: Mid-Training Bridges LLMs to Time Series Understandingcited by 3
  22. 2025Can Time-Series Foundation Models Perform Building Energy Management Tasks?cited by 2
  23. 2025Towards Interpretable and Trustworthy Time Series Reasoning: A BlueSky Visioncited by 2
  24. 2026Rethinking Post-Training Recipes for Multimodal Time-Series Forecastingcited by 2
  25. 2026Harnessing Generalist Agents for Contextualized Time Seriescited by 2
  26. 2026TSRouter: Dynamic Modality-Model Selection for Time Series Reasoningcited by 2
  27. 2025Chain-of-thought Reviewing and Correction for Time Series Question Answeringcited by 1
  28. 2026SenTSR-Bench: Thinking with Injected Knowledge for Time-Series Reasoningcited by 1
  29. 2026Janus-Q: End-to-End Event-Driven Trading via Hierarchical-Gated Reward Modelingcited by 1
  30. 2026CAN-QA: A Question-Answering Benchmark for Reasoning over In-Vehicle CAN Trafficcited by 1
  31. 2026AION: Next-Generation Tasks and Practical Harness for Time Seriescited by 1
  32. 2026Towards Verifiable Agentic Data Science: Solving Irregular TSQA Via Tool-Grounded Reasoningcited by 1
  33. 2026ReasonLab: A Controlled and Auditable Evaluation of Prompting Techniques for Multiple-Choice QAcited by 1
  34. 2026Decoupling Perception from Description: Computation-Grounded Representation Alignment between Multivariate Time Series and Languagecited by 1
  35. 2025From Time Series Analysis to Question Answering: A Survey in the LLM Eracited by 0
  36. 2025Human-AI Collaborative Bot Detection in MMORPGscited by 0
  37. 2025DiffNator: Generating Structured Explanations of Time-Series Differencescited by 0
  38. 2025Can VLM Pseudo-Labels Train a Time-Series QA Model That Outperforms the VLM?cited by 0

50 most cited of 74 All 74 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2026TS-Skill: A Benchmark for Evaluating Analytical Skills in Time-Series Question Answering
  2. 2025Chat-TS: Enhancing Multi-Modal Reasoning Over Time-Series and Natural Language Data
  3. 2026TS-Haystack: A Multi-Task Retrieval Benchmark for Long-Context Time-Series Reasoning
  4. 2022ForecastTKGQuestions: A Benchmark for Temporal Question Answering and Forecasting over Temporal Knowledge Graphs
  5. 2026From Recognition to Understanding: Unlocking Cognitive Time Series Reasoning with LLMs
  6. 2026PATRA: Pattern-Aware Alignment and Balanced Reasoning for Time Series Question Answering
  7. 2025TsLLM: Augmenting LLMs for General Time Series Understanding and Prediction
  8. 2026Zero-Shot Time-Series Question Answering via Decoupled Perception and Reasoning