mlsanityData to 14 Oct 2026

TOKON: TOKenization-Optimized Normalization for time series analysis with a large language model

arXiv 2502.05701 ↗First posted 8 Feb 2025cs.LGcited by 2

Not on the map. Why?

Abstract (arXiv)

While large language models have rapidly evolved towards general artificial intelligence, their versatility in analyzing time series data remains limited. To address this limitation, we propose a novel normalization technique that considers the inherent nature of tokenization. The proposed Tokenization-Optimized Normalization (TOKON) simplifies time series data by representing each element with a single token, effectively reducing the number of tokens by 2 to 3 times. Additionally, we introduce a novel prompt for time series forecasting, termed Time Series Forecasting with Care (TFSC), to further enhance forecasting performance. Experimental results demonstrate that TOKON improves root mean square error (RMSE) for multi-step forecasting by approximately 7% to 18%, depending on the dataset and prompting method. Furthermore, TFSC, when used in conjunction with TOKON, shows additional improvements in forecasting accuracy for certain datasets

Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Builds on 15 of its 21 references that are in the map. First posted on arXiv 8 Feb 2025.

Builds on

15 of 21 references.

References · 15

  1. 2023Time-LLM: Time Series Forecasting by Reprogramming Large Language Modelscited by 700
  2. 2023One Fits All:Power General Time Series Analysis by Pretrained LMcited by 632
  3. 2024MM-LLMs: Recent Advances in MultiModal Large Language Modelscited by 278
  4. 2023Large Language Models as General Pattern Machinescited by 197
  5. 2023TEMPO: Prompt-based Generative Pre-trained Transformer for Time Series Forecastingcited by 174
  6. 2022PromptCast: A New Prompt-based Learning Paradigm for Time Series Forecastingcited by 172
  7. 2023TEST: Text Prototype Aligned Embedding to Activate LLM's Ability for Time Seriescited by 169
  8. 2023LLM4TS: Aligning Pre-Trained LLMs as Data-Efficient Time-Series Forecasterscited by 129
  9. 2023Temporal Data Meets LLM -- Explainable Financial Time Series Forecastingcited by 77
  10. 2023Frozen Language Model Helps ECG Zero-Shot Learningcited by 62
  11. 2024LSTPrompt: Large Language Models as Zero-Shot Time Series Forecasters by Long-Short-Term Promptingcited by 59
  12. 2024Time Series Forecasting with LLMs: Understanding and Enhancing Model Capabilitiescited by 48
3 more
  1. 2024A Review of Multi-Modal Large Language and Vision Modelscited by 30
  2. 2023Extended Deep Adaptive Input Normalization for Preprocessing Time Series Data for Neural Networkscited by 2
  3. 2024UnitNorm: Rethinking Normalization for Transformers in Time Seriescited by 2

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 2.

2 papers.

  1. 2026Notation Matters: A Benchmark Study of Token-Optimized Formats in Agentic AI Systemscited by 1
  2. 2026Data-Driven Forecasting of three-Component Seismograms Using Transformer Architecturescited by 1