Continuously Updating Digital Twins using Large Language Models
This addresses the need for continuously updating digital twins in complex, dynamic environments, offering a novel approach to overcome limitations of current fixed methods.
The paper tackles the problem of digital twins struggling to adapt to constantly changing real-world systems by framing digital twinning as an in-context learning problem using large language models, resulting in CALM-DT, which achieves competitive performance and can adapt to changes without parameter updates.
Digital twins are models of real-world systems that can simulate their dynamics in response to potential actions. In complex settings, the state and action variables, and available data and knowledge relevant to a system can constantly change, requiring digital twins to continuously update with these changes to remain relevant. Current approaches struggle in this regard, as they require fixed, well-defined modelling environments, and they cannot adapt to novel variables without re-designs, or incorporate new information without re-training. To address this, we frame digital twinning as an in-context learning problem using large language models, enabling seamless updates to the twin at inference time. We develop CALM-DT, a Context-Adaptive Language Model-based Digital Twin that can accurately simulate across diverse state-action spaces using in-context learning alone by utilising fine-tuned encoders for sample retrieval. We empirically demonstrate CALM-DT's competitive performance with existing digital twin approaches, and its unique ability to adapt to changes in its modelling environment without parameter updates.