Large Language Models for Explainable Decisions in Dynamic Digital Twins

TL;DR

This paper investigates using large language models to enhance explainability in dynamic digital twins, enabling natural language explanations of autonomous decisions within complex systems like smart agriculture.

Contribution

It introduces a novel approach of integrating LLMs with DDTs to generate understandable explanations, bridging technical complexity and user comprehension.

Findings

LLMs can effectively generate natural language explanations for DDT decisions.

The approach improves transparency and user trust in autonomous systems.

Case study demonstrates practical applicability in smart agriculture.

Abstract

Dynamic data-driven Digital Twins (DDTs) can enable informed decision-making and provide an optimisation platform for the underlying system. By leveraging principles of Dynamic Data-Driven Applications Systems (DDDAS), DDTs can formulate computational modalities for feedback loops, model updates and decision-making, including autonomous ones. However, understanding autonomous decision-making often requires technical and domain-specific knowledge. This paper explores using large language models (LLMs) to provide an explainability platform for DDTs, generating natural language explanations of the system's decision-making by leveraging domain-specific knowledge bases. A case study from smart agriculture is presented.