LLMs as Master Forgers: Generating Synthetic Time Series Data for Manufacturing
Results demonstrate that the LLM-driven framework outperforms traditional time series modeling techniques like ARIMA and LSTMs, generating high-quality synthetic time series data that effectively captures temporal dependencies and statistical properties of real manufacturing data, leading to improvements in downstream...
Mantek Singh, Jeshwanth Challagundla, Prateek Karnal et al.
· 2024 International Conferenc... · 5 citations