Exploring LLMs for Causal Discovery in Cyber-Physical Systems

Katrin Ehrenmüller, Paul Maurer, Fajar J. Ekaputra, Marta Sabou, Konrad Diwold

Keywords: Causality, Large-Language Models, Cyber-Physical Systems, Explainability

TL;DR: This paper explores how LLMs can assist domain experts in causal discovery for CPS by suggesting potential system states and causal relations.

Abstract: Causality plays a fundamental role in both human reasoning and complex system analysis. As Cyber-Physical Systems (CPS) become increasingly complex, understanding causal relationships between system events is essential for tasks such as anomaly detection and fault diagnosis. This paper explores the potential of Large Language Models (LLMs) to support causal discovery in CPS by assisting domain experts in identifying system states and causal relations between those. We propose a hybrid workflow that integrates LLM-generated suggestions with domain expert validation, aiming to improve the efficiency of causal analysis. Our evaluation is conducted on a real-world smart grid use case and compares LLM-generated causal relations with domain expert-validated ground truth. The results indicate that, while LLMs can propose relevant causal structures, their effectiveness varies depending on the complexity of temporal and topological relationships. Although these models do not replace human domain expertise, they can serve as a valuable tool for supporting causal discovery in a hybrid workflow. Future research should focus on refining LLM capabilities and expanding their application across different CPS domains. Investigating different LLMs, causal models, and larger datasets may provide deeper insights into their potential for causal discovery.

Submission Number: 1