mlsanityData to 14 Oct 2026

Temporal Data Meets LLM -- Explainable Financial Time Series Forecasting

arXiv 2306.11025 ↗First posted 19 Jun 2023cs.LG cs.AI cs.CLcited by 77

On the map: LLM reasoning → Reasoning for agents, planning and code

Abstract (arXiv)

This paper presents a novel study on harnessing Large Language Models' (LLMs) outstanding knowledge and reasoning abilities for explainable financial time series forecasting. The application of machine learning models to financial time series comes with several challenges, including the difficulty in cross-sequence reasoning and inference, the hurdle of incorporating multi-modal signals from historical news, financial knowledge graphs, etc., and the issue of interpreting and explaining the model results. In this paper, we focus on NASDAQ-100 stocks, making use of publicly accessible historical stock price data, company metadata, and historical economic/financial news. We conduct experiments to illustrate the potential of LLMs in offering a unified solution to the aforementioned challenges. Our experiments include trying zero-shot/few-shot inference with GPT-4 and instruction-based fine-tuning with a public LLM model Open LLaMA. We demonstrate our approach outperforms a few baselines, including the widely applied classic ARMA-GARCH model and a gradient-boosting tree model. Through the performance comparison results and a few examples, we find LLMs can make a well-thought decision by reasoning over information from both textual news and price time series and extracting insights, leveraging cross-sequence information, and utilizing the inherent knowledge embedded within the LLM. Additionally, we show that a publicly available LLM such as Open-LLaMA, after fine-tuning, can comprehend the instruction to generate explainable forecasts and achieve reasonable performance, albeit relatively inferior in comparison to GPT-4.

Key facts. Cited by 77 papers in the map (data through 14 Oct 2026). Placed in Reasoning for agents, planning and code, one of 17 directions in LLM reasoning. Builds on 20 of its 76 references that are in the map. First posted on arXiv 19 Jun 2023.

Builds on

20 of 76 references.

References · 20

  1. 2020Language Models are Few-Shot Learnerscited by 32,419
  2. 2023LLaMA: Open and Efficient Foundation Language Modelscited by 14,132
  3. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,459
  4. 2023Let's Verify Step by Stepcited by 3,789
  5. 2023A Survey of Large Language Modelscited by 2,576
  6. 2022Solving Quantitative Reasoning Problems with Language Modelscited by 1,392
  7. 2023BloombergGPT: A Large Language Model for Financecited by 939
  8. 2023Multimodal Chain-of-Thought Reasoning in Language Modelscited by 752
  9. 2023Instruction Tuning with GPT-4cited by 686
  10. 2020A Generalization of Transformer Networks to Graphscited by 661
  11. 2019Graph Transformer Networkscited by 523
  12. 2019Financial Time Series Forecasting with Deep Learning : A Systematic Literature Review: 2005-2019cited by 273
8 more
  1. 2023MathPrompter: Mathematical Reasoning using Large Language Modelscited by 236
  2. 2020Graph-Bert: Only Attention is Needed for Learning Graph Representationscited by 177
  3. 2021An Experimental Review on Deep Learning Architectures for Time Series Forecastingcited by 47
  4. 2018Deep Learning with Long Short-Term Memory for Time Series Predictioncited by 39
  5. 2021Temporal Latent Auto-Encoder: A Method for Probabilistic Multivariate Time Series Forecastingcited by 32
  6. 2023On Efficient Training of Large-Scale Deep Learning Models: A Literature Reviewcited by 26
  7. 2018A generalized financial time series forecasting model based on automatic feature engineering using genetic algorithms and support vector machinecited by 2
  8. 2018Correlated Anomaly Detection from Large Streaming Datacited by 1

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 6; 2024: 21; 2025: 41; 2026: 9.

77 papers.

Sort:

By area:

  1. 2023TEMPO: Prompt-based Generative Pre-trained Transformer for Time Series Forecastingcited by 174
  2. 2024Retrieval-Augmented Generation with Graphs (GraphRAG)cited by 172
  3. 2024Large Language Models for Time Series: A Surveycited by 114
  4. 2023Large Models for Time Series and Spatio-Temporal Data: A Survey and Outlookcited by 110
  5. 2024Revolutionizing Finance with LLMs: An Overview of Applications and Insightscited by 90
  6. 2024A Survey of Large Language Models for Financial Applications: Progress, Prospects and Challengescited by 90
  7. 2024Time-MMD: Multi-Domain Multimodal Dataset for Time Series Analysiscited by 74
  8. 2024Empowering Time Series Analysis with Large Language Models: A Surveycited by 60
  9. 2025MTBench: A Multimodal Time Series Benchmark for Temporal Reasoning and Question Answeringcited by 55
  10. 2024Position: What Can Large Language Models Tell Us about Time Series Analysiscited by 47
  11. 2025TimeXL: Explainable Multi-modal Time Series Prediction with LLM-in-the-Loopcited by 39
  12. 2023Exploring Large Language Models for Human Mobility Prediction under Public Eventscited by 34
38 more
  1. 2024Deep Learning for Cross-Domain Data Fusion in Urban Computing: Taxonomy, Advances, and Outlookcited by 33
  2. 2024Large Language Models can Deliver Accurate and Interpretable Time Series Anomaly Detectioncited by 29
  3. 2024Multi-Patch Prediction: Adapting LLMs for Time Series Representation Learningcited by 25
  4. 2024Large Language Models for Manufacturingcited by 24
  5. 2024Towards Modeling Learner Performance with Large Language Modelscited by 21
  6. 2025Data Poisoning in Deep Learning: A Surveycited by 20
  7. 2025T2S: High-resolution Time Series Generation with Text-to-Series Diffusion Modelscited by 20
  8. 2023User Modeling in the Era of Large Language Models: Current Research and Future Directionscited by 18
  9. 2024GraphInsight: Unlocking Insights in Large Language Models for Graph Structure Understandingcited by 18
  10. 2024TimeRAF: Retrieval-Augmented Foundation model for Zero-shot Time Series Forecastingcited by 17
  11. 2024Large Language Models for Mobility Analysis in Transportation Systems: A Survey on Forecasting Taskscited by 16
  12. 2025LLM/Agent-as-Data-Analyst: A Surveycited by 16
  13. 2023Unveiling the Potential of Sentiment: Can Large Language Models Predict Chinese Stock Price Movements?cited by 15
  14. 2024A Survey of Generative Techniques for Spatial-Temporal Data Miningcited by 14
  15. 2025Knowledge or Reasoning? A Close Look at How LLMs Think Across Domainscited by 14
  16. 2025Retrieval-augmented Large Language Models for Financial Time Series Forecastingcited by 12
  17. 2025A Survey on Mathematical Reasoning and Optimization with Large Language Modelscited by 12
  18. 2025BEDTime: A Unified Benchmark for Automatically Describing Time Seriescited by 12
  19. 2023Humans vs Large Language Models: Judgmental Forecasting in an Era of Advanced AIcited by 11
  20. 2025Unraveling Spatio-Temporal Foundation Models via the Pipeline Lens: A Comprehensive Reviewcited by 10
  21. 2025Multimodal Conditioned Diffusive Time Series Forecastingcited by 9
  22. 2025Reasoning on Time-Series for Financial Technical Analysiscited by 5
  23. 2024LLMForecaster: Improving Seasonal Event Forecasts with Unstructured Textual Datacited by 4
  24. 2025Will LLMs be Professional at Fund Investment? DeepFund: A Live Arena Perspectivecited by 4
  25. 2025DELPHYNE: A Pre-Trained Model for General and Financial Time Seriescited by 4
  26. 2024Exploring LLM Cryptocurrency Trading Through Fact-Subjectivity Aware Reasoningcited by 3
  27. 2025A Multi-Modal Knowledge-Enhanced Framework for Vessel Trajectory Predictioncited by 3
  28. 2025Do Large Language Models Know Conflict? Investigating Parametric vs. Non-Parametric Knowledge of LLMs for Conflict Forecastingcited by 3
  29. 2025Large Language models for Time Series Analysis: Techniques, Applications, and Challengescited by 3
  30. 2025MASCA: LLM based-Multi Agents System for Credit Assessmentcited by 3
  31. 2025TimeSense:Making Large Language Models Proficient in Time-Series Analysiscited by 3
  32. 2025Insight Miner: A Time Series Analysis Dataset for Cross-Domain Alignment with Natural Languagecited by 3
  33. 2024Enhancing Traffic Prediction with Textual Data Using Large Language Modelscited by 2
  34. 2025TOKON: TOKenization-Optimized Normalization for time series analysis with a large language modelcited by 2
  35. 2025Bridging Distribution Gaps in Time Series Foundation Model Pretraining with Prototype-Guided Normalizationcited by 2
  36. 2025iTFKAN: Interpretable Time Series Forecasting with Kolmogorov-Arnold Networkcited by 2
  37. 2025Beyond Fixed Patches: Enhancing GPTs for Financial Prediction with Adaptive Segmentation and Learnable Waveletscited by 2
  38. 2025In-Context and Few-Shots Learning for Forecasting Time Series Data based on Large Language Modelscited by 2

50 most cited of 77 All 77 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2025AI Analyst: Framework and Comprehensive Evaluation of Large Language Models for Financial Time Series Report Generation
  2. 2026Reasoning through Verifiable Forecast Actions: Consistency-Grounded RL for Financial LLMs
  3. 2025TsLLM: Augmenting LLMs for General Time Series Understanding and Prediction
  4. 2025VISTA: Vision-Language Inference for Training-Free Stock Time-Series Analysis
  5. 2025Knowledge Graph Construction for Stock Markets with LLM-Based Explainable Reasoning
  6. 2026LLM-based Agents for Forecasting and Prediction: Methods, Training, Evaluation, and Applications
  7. 2026TimeSeriesExamAgent: Creating Time Series Reasoning Benchmarks at Scale
  8. 2025TS-Reasoner: Aligning Time Series Foundation Models with LLM Reasoning