LLMs as Master Forgers: Generating Synthetic Time Series Data for Manufacturing

arXiv:2609.16155v1 Announce Type: cross Abstract: This paper presents a novel framework leveraging Large Language Models (LLMs) to generate synthetic time series data for manufacturing processes. Motivated by the scarcity of labeled time-series data in real-world manufacturing settings, which hinders the development of robust machine learning models, we explore the potential of LLMs to learn complex temporal dependencies and generate realistic synthetic data. Our approach involves fine-tuning pre-trained LLMs on manufacturing process instructions and employing a Retrieval Augmented Generation (RAG) technique to enhance data diversity and realism. We evaluate our method against traditional time series modeling techniques like ARIMA and LSTMs, using quantitative metrics, PCA analysis, and downstream task performance (anomaly detection). Results demonstrate that our LLM-driven framework outperforms these baselines, generating high-quality synthetic time series data that effectively captures temporal dependencies and statistical properties of real manufacturing data, leading to improvements in downstream task performance.

Related

• TimeSAF: Towards LLM-Guided Semantic Asynchronous Fusion for Time Series Forecasting
• Feasible and Novel Synthetic Population Generation with Tabular and Sequential Travel Attributes
• Do LLMs Understand Limit Order Book Dynamics?
• Make LLM Learn to Synthesize from Streaming Experiences through Feedback

Source: arXiv cs.AI | 2026-09-16