Forging Time Series with Language: A Large Language Model Approach to Synthetic Data Generation

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Rousseau, Cécile, Boschi, Tobia, Cornacchia, Giandomenico, Salwala, Dhaval, Pascale, Alessandra, Moreno, Juan Bernabe
Formato: Preprint
Publicado: 2025
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866914234612318208
author Rousseau, Cécile
Boschi, Tobia
Cornacchia, Giandomenico
Salwala, Dhaval
Pascale, Alessandra
Moreno, Juan Bernabe
author_facet Rousseau, Cécile
Boschi, Tobia
Cornacchia, Giandomenico
Salwala, Dhaval
Pascale, Alessandra
Moreno, Juan Bernabe
contents SDForger is a flexible and efficient framework for generating high-quality multivariate time series using LLMs. Leveraging a compact data representation, SDForger provides synthetic time series generation from a few samples and low-computation fine-tuning of any autoregressive LLM. Specifically, the framework transforms univariate and multivariate signals into tabular embeddings, which are then encoded into text and used to fine-tune the LLM. At inference, new textual embeddings are sampled and decoded into synthetic time series that retain the original data's statistical properties and temporal dynamics. Across a diverse range of datasets, SDForger outperforms existing generative models in many scenarios, both in similarity-based evaluations and downstream forecasting tasks. By enabling textual conditioning in the generation process, SDForger paves the way for multimodal modeling and the streamlined integration of time series with textual information. The model is open-sourced at https://github.com/IBM/fms-dgt/tree/main/fms_dgt/public/databuilders/time_series.
format Preprint
id arxiv_https___arxiv_org_abs_2505_17103
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Forging Time Series with Language: A Large Language Model Approach to Synthetic Data Generation
Rousseau, Cécile
Boschi, Tobia
Cornacchia, Giandomenico
Salwala, Dhaval
Pascale, Alessandra
Moreno, Juan Bernabe
Computation and Language
Artificial Intelligence
SDForger is a flexible and efficient framework for generating high-quality multivariate time series using LLMs. Leveraging a compact data representation, SDForger provides synthetic time series generation from a few samples and low-computation fine-tuning of any autoregressive LLM. Specifically, the framework transforms univariate and multivariate signals into tabular embeddings, which are then encoded into text and used to fine-tune the LLM. At inference, new textual embeddings are sampled and decoded into synthetic time series that retain the original data's statistical properties and temporal dynamics. Across a diverse range of datasets, SDForger outperforms existing generative models in many scenarios, both in similarity-based evaluations and downstream forecasting tasks. By enabling textual conditioning in the generation process, SDForger paves the way for multimodal modeling and the streamlined integration of time series with textual information. The model is open-sourced at https://github.com/IBM/fms-dgt/tree/main/fms_dgt/public/databuilders/time_series.
title Forging Time Series with Language: A Large Language Model Approach to Synthetic Data Generation
topic Computation and Language
Artificial Intelligence
url https://arxiv.org/abs/2505.17103